handle checking for file better

Reviewed-on: #16

.gitignore

@@ -1 +1,9 @@
 /target
+/.surrealdb
+/.minio
+perf.data
+flamegraph.svg
+perf.data.old
+/docker/logs/*
+/downloaded
+/Crawler.toml

.vscode/launch.json

@@ -7,15 +7,15 @@
         {
             "type": "lldb",
             "request": "launch",
-            "name": "Debug executable 'surreal_spider'",
+            "name": "Debug executable 'internet_mapper'",
             "cargo": {
                 "args": [
                     "build",
-                    "--bin=surreal_spider",
+                    "--bin=internet_mapper",
-                    "--package=surreal_spider"
+                    "--package=internet_mapper"
                 ],
                 "filter": {
-                    "name": "surreal_spider",
+                    "name": "internet_mapper",
                     "kind": "bin"
                 }
             },
@@ -25,16 +25,16 @@
         {
             "type": "lldb",
             "request": "launch",
-            "name": "Debug unit tests in executable 'surreal_spider'",
+            "name": "Debug unit tests in executable 'internet_mapper'",
             "cargo": {
                 "args": [
                     "test",
                     "--no-run",
-                    "--bin=surreal_spider",
+                    "--bin=internet_mapper",
-                    "--package=surreal_spider"
+                    "--package=internet_mapper"
                 ],
                 "filter": {
-                    "name": "surreal_spider",
+                    "name": "internet_mapper",
                     "kind": "bin"
                 }
             },

.vscode/settings.json

@@ -0,0 +1,8 @@
+{
+    "cSpell.words": [
+        "creds",
+        "reqwest",
+        "rustls",
+        "surql",
+    ]
+}

Cargo.toml

@@ -1,7 +1,23 @@
 [package]
-name = "surreal_spider"
+name = "internet_mapper"
 version = "0.1.0"
 edition = "2021"
 
 [dependencies]
-spider = { features = [], git="https://github.com/Rushmore75/spider.git", rev="ff91646973ad04ff423010f36206f550e37c4278" }
+base64 = "0.22.1"
+futures-util = "0.3.31"
+html5ever = "0.29"
+metrics = "0.24.1"
+metrics-exporter-prometheus = { version = "0.16.2", features=["http-listener"]}
+opentelemetry = "0.30.0"
+opentelemetry-otlp = { version = "0.30.0", features = ["metrics", "trace", "logs", "grpc-tonic"] }
+opentelemetry_sdk = "0.30.0"
+rand = "0.9.1"
+reqwest = { version = "0.12", features = ["gzip", "default", "rustls-tls", "stream"] }
+serde = { version = "1.0", features = ["derive"] }
+surrealdb = "2.2"
+tokio = { version="1.41.0", features = ["full"] }
+toml = "0.8.20"
+tracing = "0.1"
+tracing-subscriber = { version = "0.3", features = ["env-filter", "local-time", "json"] }
+url = { version = "2.5", features = ["serde"] }

Crawler.toml

@@ -0,0 +1,22 @@
+# Visability config
+# Alloy (for Tempo)
+tracing_endpoint = "http://localhost:4317"
+# Prometheus
+metrics_endpoint = "http://localhost:9090/api/v1/otlp/v1/metrics"
+# Alloy (for Loki)
+log_file = "./docker/logs/tracing.log"
+
+# Surreal config
+surreal_url = "localhost:8000"
+surreal_username = "root"
+surreal_password = "root"
+surreal_ns = "test"
+surreal_db = "v1.21.1"
+
+# Crawler config
+crawl_filter = "https://ftpgeoinfo.msl.mt.gov/Data/Spatial/MSDI/Imagery/2023_NAIP/UTM_County_Mosaics/" 
+# crawl_filter = "https://oliveratkinson.net" 
+start_url = "https://ftpgeoinfo.msl.mt.gov/Data/Spatial/MSDI/Imagery/2023_NAIP/UTM_County_Mosaics/"
+# start_url = "https://oliveratkinson.net"
+budget = 100
+batch_size = 2

README.md

@@ -1,23 +1,59 @@
 # Surreal Crawler
 
-Mapping with a budget of 1000 (crawl 1000 sites, so many more links are actually discovered), on [my webiste](https://oliveratkinson.net) on 8/26/2024 took 1m9s.
+Crawls sites saving all the found links to a surrealdb database. It then proceeds to take batches of 100 uncrawled links untill the crawl budget is reached. It saves the data of each site in a minio database.
 
-This is including the crawl and loading into the database and linking sites. (Locally hosted surreal db instance)
+## How to use
 
-This run created 4299 site links with 23286 links between the sites. (It found my this git site which really bolsters those numbers.)
+1. Clone the repo and `cd` into it.
+2. Build the repo with `cargo build -r`
+3. Start the docker conatiners
+	1. cd into the docker folder `cd docker`
+	2. Bring up the docker containers `docker compose up -d`
+4. From the project's root, edit the `Crawler.toml` file to your liking.
+5. Run with `./target/release/internet_mapper`
 
-## Install / Build
+You can view stats of the project at `http://<your-ip>:3000/dashboards`
 
-* You will need rust to compile the crawler [rustup.rs](https://rustup.rs)
+```bash
-* You need python3 (will come installed on most linux distros) and poetry for dependancy management.
+# Untested script but probably works
-    * Install `pipx`, `python3`
+git clone https://git.oliveratkinson.net/Oliver/internet_mapper.git
-    * Then: `pipx install poetry`
+cd internet_mapper
-    * Then: `poetry install` to install the project dependancies
-* You need to install [surrealdb](https://surrealdb.com)
 
-## Use
+cargo build -r
 
-Just run `./crawl.sh {url}` and it will start crawling. You can tweak the budget inside [crawl.sh](https://git.oliveratkinson.net/Oliver/internet_mapper/src/branch/main/crawl.sh) if you want.
+cd docker
+docker compose up -d
+cd ..
 
-You can also prefix the command with `time` to benchmark the system, such as: `time ./crawl.sh https://discord.com`.
+$EDITOR Crawler.toml
+
+./target/release/internet_mapper
+
+```
+
+### TODO
+
+- [x] Domain filtering - prevent the crawler from going on alternate versions of wikipedia.
+- [ ] Conditionally save content - based on filename or file contents
+- [x] GUI / TUI ? - Graphana
+- [x] Better asynchronous getting of the sites. Currently it all happens serially.
+- [x] Allow for storing asynchronously - dropping the "links to" logic fixes this need
+- [x] Control crawler via config file (no recompliation needed)
+
+### Feats
+
+3/17/25: Took >1hr to crawl 100 pages.
+
+3/19/25: Took 20min to crawl 1000 pages.
+This ment we stored 1000 pages, 142,997 urls, and 1,425,798 links between the two.
+
+3/20/25: Took 5min to crawl 1000 pages.
+
+3/21/25: Took 3min to crawl 1000 pages.
+
+7/.../25: Downloaded just shy of 12TB of data from a remote server.
+
+# About
+
+![Screenshot](/pngs/graphana.png)
 

compose.yml

@@ -1,13 +0,0 @@
-services:
-  db:
-    image: surrealdb/surrealdb:latest-dev
-    ports:
-    - 8000:8000
-    command:
-      - start
-      - --log
-      - debug
-      - --user
-      - root
-      - --pass
-      - root

crawl.sh

@@ -1,2 +0,0 @@
-#!/bin/bash
-cargo run -- $1 1000 | python3 driver.py

demo_site/index.html

@@ -0,0 +1,24 @@
+<!DOCTYPE html>
+<html>
+<head>
+    <title>Page Title</title>
+    <script src='main.js'></script>
+	<base href="/" target="_blank">
+	<link rel="stylesheet" href="style.css">
+</head>
+<body>
+    <a href="/">Link text</a>
+	<img src="/picture.png"></img>
+	<audio src="/audio.mp3" controls>Audio is unsupported</audio>
+	<video src="/video.mp4" controls>Video is unsupported</video>
+	<audio controls>
+		<source src="audio.mp3"></source>
+	</audio>
+	<map>
+		<area href="/"></area>
+	</map>
+	<object data="/video.mp4"></object>
+	<iframe src="/" title="The same Site"></iframe>
+	<meta>
+</body>
+</html>

demo_site/script.js

@@ -0,0 +1 @@
+alert("alert")

demo_site/style.css

@@ -0,0 +1,3 @@
+html {
+	background-color: white;
+}

docker/alloy.conf

@@ -0,0 +1,36 @@
+local.file_match "tmplogs" {
+    path_targets = [{"__path__" = "/tmp/alloy-logs/*.log"}]
+}
+
+loki.source.file "local_files" {
+    targets    	= local.file_match.tmplogs.targets
+    forward_to 	= [loki.write.local_loki.receiver]
+}
+
+loki.write "local_loki" {
+    endpoint {
+        url = "http://loki:3100/loki/api/v1/push"
+    }
+}
+
+otelcol.receiver.otlp "otlp_receiver" {
+  grpc {
+    endpoint = "0.0.0.0:4317"
+  }
+  http {
+    endpoint = "0.0.0.0:4318"
+  }
+
+  output {
+    traces = [otelcol.exporter.otlp.tempo.input,]
+  }
+}
+
+otelcol.exporter.otlp "tempo" {
+  client {
+    endpoint = "tempo:4317"
+    tls {
+			insecure = true
+		}
+  }
+}

docker/compose.yml

@@ -0,0 +1,92 @@
+services:
+
+  # Database
+  surreal:
+    image: surrealdb/surrealdb:latest-dev
+    ports:
+    - 8000:8000
+    volumes:
+      - surrealdb_storage:/mydata
+    command:
+      - start
+      - --log
+      - debug
+      - --user
+      - root
+      - --pass
+      - root
+      - rocksdb:/mydata/database.db
+
+  # Tracing
+  tempo:
+    image: grafana/tempo:latest
+    command: [ "-config.file=/etc/tempo.yaml" ]
+    volumes:
+      - ./tempo.yaml:/etc/tempo.yaml
+      - tempo_storage:/var/tempo
+    ports:
+      - 3200:3200 # self metrics for prometheus
+      - 4317:4317 # otlp grpc - (alloy) 
+
+  # Log scraper
+  alloy:
+    image: grafana/alloy:latest
+    ports:
+      - 12345:12345
+    volumes:
+      # if you change this, you also need to change it in the alloy config file
+      - ./logs/:/tmp/alloy-logs
+      - ./alloy.conf:/etc/alloy/config.alloy
+      - alloy_storage:/var/lib/alloy
+    command:
+      - run
+      - --server.http.listen-addr=0.0.0.0:12345
+      - --storage.path=/var/lib/alloy/data
+      - /etc/alloy/config.alloy
+
+  # Log storage / analysis
+  loki:
+    image: grafana/loki:latest
+    ports:
+      - 3100:3100
+    command: -config.file=/etc/loki/local-config.yaml
+    volumes:
+      - ./loki.yaml:/etc/loki/local-config.yaml
+
+  # Metrics
+  prometheus:
+    image: prom/prometheus:latest
+    ports:
+      - 9090:9090
+    volumes:
+      - ./prometheus.yaml:/etc/prometheus/prometheus.yml
+      # persist data
+      # - prometheus_storage:/prometheus
+    command:
+      - --enable-feature=native-histograms
+      - --web.enable-remote-write-receiver
+      - --web.enable-lifecycle
+      - --web.enable-otlp-receiver
+      - --config.file=/etc/prometheus/prometheus.yml
+
+  # Everything viewer
+  grafana:
+    image: grafana/grafana:latest
+    volumes:
+      - ./grafana.yaml:/etc/grafana/provisioning/datasources/datasources.yaml
+      - ./dashboards:/var/lib/grafana/dashboards
+      - grafana_storage:/var/lib/grafana
+    environment:
+      - GF_AUTH_ANONYMOUS_ENABLED=true
+      - GF_AUTH_ANONYMOUS_ORG_ROLE=Admin
+      - GF_AUTH_DISABLE_LOGIN_FORM=true
+      - GF_FEATURE_TOGGLES_ENABLE=traceqlEditor
+    ports:
+      - 3000:3000
+  
+volumes:
+  prometheus_storage:
+  grafana_storage:
+  alloy_storage:
+  surrealdb_storage:
+  tempo_storage:

docker/dashboards/crawler-dashboard.json

@@ -0,0 +1,648 @@
+{
+  "__inputs": [
+    {
+      "name": "DS_PROMETHEUS",
+      "label": "Prometheus",
+      "description": "",
+      "type": "datasource",
+      "pluginId": "prometheus",
+      "pluginName": "Prometheus"
+    },
+    {
+      "name": "DS_LOKI",
+      "label": "Loki",
+      "description": "",
+      "type": "datasource",
+      "pluginId": "loki",
+      "pluginName": "Loki"
+    }
+  ],
+  "__elements": {},
+  "__requires": [
+    {
+      "type": "grafana",
+      "id": "grafana",
+      "name": "Grafana",
+      "version": "11.3.1"
+    },
+    {
+      "type": "panel",
+      "id": "logs",
+      "name": "Logs",
+      "version": ""
+    },
+    {
+      "type": "datasource",
+      "id": "loki",
+      "name": "Loki",
+      "version": "1.0.0"
+    },
+    {
+      "type": "datasource",
+      "id": "prometheus",
+      "name": "Prometheus",
+      "version": "1.0.0"
+    },
+    {
+      "type": "panel",
+      "id": "stat",
+      "name": "Stat",
+      "version": ""
+    },
+    {
+      "type": "panel",
+      "id": "timeseries",
+      "name": "Time series",
+      "version": ""
+    }
+  ],
+  "annotations": {
+    "list": [
+      {
+        "builtIn": 1,
+        "datasource": {
+          "type": "grafana",
+          "uid": "-- Grafana --"
+        },
+        "enable": true,
+        "hide": true,
+        "iconColor": "rgba(0, 211, 255, 1)",
+        "name": "Annotations & Alerts",
+        "type": "dashboard"
+      }
+    ]
+  },
+  "editable": true,
+  "fiscalYearStartMonth": 0,
+  "graphTooltip": 0,
+  "id": null,
+  "links": [],
+  "panels": [
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "barWidthFactor": 0.6,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": 300000,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          }
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 8,
+        "x": 0,
+        "y": 0
+      },
+      "id": 5,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "pluginVersion": "11.3.1",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "surql_trips",
+          "fullMetaSearch": false,
+          "includeNullMetadata": true,
+          "legendFormat": "Trips to Surreal",
+          "range": true,
+          "refId": "A",
+          "useBackend": false
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "s3_trips",
+          "fullMetaSearch": false,
+          "hide": false,
+          "includeNullMetadata": true,
+          "instant": false,
+          "legendFormat": "Trips to S3",
+          "range": true,
+          "refId": "B",
+          "useBackend": false
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "pages_crawled",
+          "fullMetaSearch": false,
+          "hide": false,
+          "includeNullMetadata": true,
+          "instant": false,
+          "legendFormat": "total crawled",
+          "range": true,
+          "refId": "C",
+          "useBackend": false
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "pages_being_processed",
+          "fullMetaSearch": false,
+          "hide": false,
+          "includeNullMetadata": true,
+          "instant": false,
+          "legendFormat": "Pages being processed",
+          "range": true,
+          "refId": "E",
+          "useBackend": false
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "gets_in_flight",
+          "fullMetaSearch": false,
+          "hide": false,
+          "includeNullMetadata": true,
+          "instant": false,
+          "legendFormat": "__auto",
+          "range": true,
+          "refId": "D",
+          "useBackend": false
+        }
+      ],
+      "title": "Crawler stats",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "palette-classic"
+          },
+          "custom": {
+            "axisBorderShow": false,
+            "axisCenteredZero": false,
+            "axisColorMode": "text",
+            "axisLabel": "",
+            "axisPlacement": "auto",
+            "barAlignment": 0,
+            "barWidthFactor": 0.6,
+            "drawStyle": "line",
+            "fillOpacity": 0,
+            "gradientMode": "none",
+            "hideFrom": {
+              "legend": false,
+              "tooltip": false,
+              "viz": false
+            },
+            "insertNulls": false,
+            "lineInterpolation": "linear",
+            "lineWidth": 1,
+            "pointSize": 5,
+            "scaleDistribution": {
+              "type": "linear"
+            },
+            "showPoints": "auto",
+            "spanNulls": 300000,
+            "stacking": {
+              "group": "A",
+              "mode": "none"
+            },
+            "thresholdsStyle": {
+              "mode": "off"
+            }
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              },
+              {
+                "color": "red",
+                "value": 80
+              }
+            ]
+          }
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 9,
+        "x": 8,
+        "y": 0
+      },
+      "id": 6,
+      "options": {
+        "legend": {
+          "calcs": [],
+          "displayMode": "list",
+          "placement": "bottom",
+          "showLegend": true
+        },
+        "tooltip": {
+          "mode": "single",
+          "sort": "none"
+        }
+      },
+      "pluginVersion": "11.3.1",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "surql_trips",
+          "fullMetaSearch": false,
+          "includeNullMetadata": true,
+          "legendFormat": "Trips to Surreal",
+          "range": true,
+          "refId": "A",
+          "useBackend": false
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "surql_link_calls",
+          "fullMetaSearch": false,
+          "hide": false,
+          "includeNullMetadata": true,
+          "instant": false,
+          "legendFormat": "link calls",
+          "range": true,
+          "refId": "B",
+          "useBackend": false
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "surql_store_calls",
+          "fullMetaSearch": false,
+          "hide": false,
+          "includeNullMetadata": true,
+          "instant": false,
+          "legendFormat": "store calls",
+          "range": true,
+          "refId": "C",
+          "useBackend": false
+        },
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "pages_being_processed",
+          "fullMetaSearch": false,
+          "hide": false,
+          "includeNullMetadata": true,
+          "instant": false,
+          "legendFormat": "Pages being processed",
+          "range": true,
+          "refId": "E",
+          "useBackend": false
+        }
+      ],
+      "title": "Surreal stats",
+      "type": "timeseries"
+    },
+    {
+      "datasource": {
+        "type": "prometheus",
+        "uid": "${DS_PROMETHEUS}"
+      },
+      "description": "This is across all threads, so this isn't wall clock time",
+      "fieldConfig": {
+        "defaults": {
+          "color": {
+            "mode": "thresholds"
+          },
+          "mappings": [],
+          "thresholds": {
+            "mode": "absolute",
+            "steps": [
+              {
+                "color": "green",
+                "value": null
+              }
+            ]
+          },
+          "unit": "ms"
+        },
+        "overrides": []
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 7,
+        "x": 17,
+        "y": 0
+      },
+      "id": 7,
+      "options": {
+        "colorMode": "value",
+        "graphMode": "area",
+        "justifyMode": "auto",
+        "orientation": "auto",
+        "percentChangeColorMode": "standard",
+        "reduceOptions": {
+          "calcs": [
+            "lastNotNull"
+          ],
+          "fields": "",
+          "values": false
+        },
+        "showPercentChange": false,
+        "textMode": "auto",
+        "wideLayout": true
+      },
+      "pluginVersion": "11.3.1",
+      "targets": [
+        {
+          "datasource": {
+            "type": "prometheus",
+            "uid": "${DS_PROMETHEUS}"
+          },
+          "disableTextWrap": false,
+          "editorMode": "builder",
+          "expr": "surql_lock_waiting_ms",
+          "fullMetaSearch": false,
+          "includeNullMetadata": true,
+          "legendFormat": "__auto",
+          "range": true,
+          "refId": "A",
+          "useBackend": false
+        }
+      ],
+      "title": "Time spend waiting on lock",
+      "type": "stat"
+    },
+    {
+      "datasource": {
+        "type": "loki",
+        "uid": "${DS_LOKI}"
+      },
+      "gridPos": {
+        "h": 18,
+        "w": 24,
+        "x": 0,
+        "y": 8
+      },
+      "id": 1,
+      "options": {
+        "dedupStrategy": "none",
+        "enableLogDetails": true,
+        "prettifyLogMessage": false,
+        "showCommonLabels": false,
+        "showLabels": false,
+        "showTime": false,
+        "sortOrder": "Descending",
+        "wrapLogMessage": false
+      },
+      "pluginVersion": "11.3.1",
+      "targets": [
+        {
+          "datasource": {
+            "type": "loki",
+            "uid": "${DS_LOKI}"
+          },
+          "editorMode": "code",
+          "expr": "{filename=\"/tmp/alloy-logs/tracing.log\"} | json | level = `ERROR` | line_format \"{{.threadId}} {{.filename_extracted}}:{{.line_number}}  {{.fields_message}}\"",
+          "queryType": "range",
+          "refId": "A"
+        }
+      ],
+      "title": "Errors",
+      "type": "logs"
+    },
+    {
+      "datasource": {
+        "type": "loki",
+        "uid": "${DS_LOKI}"
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 26
+      },
+      "id": 2,
+      "options": {
+        "dedupStrategy": "none",
+        "enableLogDetails": true,
+        "prettifyLogMessage": false,
+        "showCommonLabels": false,
+        "showLabels": false,
+        "showTime": false,
+        "sortOrder": "Descending",
+        "wrapLogMessage": false
+      },
+      "pluginVersion": "11.3.1",
+      "targets": [
+        {
+          "datasource": {
+            "type": "loki",
+            "uid": "${DS_LOKI}"
+          },
+          "editorMode": "code",
+          "expr": "{filename=\"/tmp/alloy-logs/tracing.log\"} | json | level = `DEBUG` | line_format \"{{.fields_message}}\"",
+          "queryType": "range",
+          "refId": "A"
+        }
+      ],
+      "title": "Debug",
+      "type": "logs"
+    },
+    {
+      "datasource": {
+        "type": "loki",
+        "uid": "${DS_LOKI}"
+      },
+      "gridPos": {
+        "h": 16,
+        "w": 12,
+        "x": 12,
+        "y": 26
+      },
+      "id": 4,
+      "options": {
+        "dedupStrategy": "none",
+        "enableLogDetails": true,
+        "prettifyLogMessage": false,
+        "showCommonLabels": false,
+        "showLabels": false,
+        "showTime": false,
+        "sortOrder": "Descending",
+        "wrapLogMessage": false
+      },
+      "pluginVersion": "11.3.1",
+      "targets": [
+        {
+          "datasource": {
+            "type": "loki",
+            "uid": "${DS_LOKI}"
+          },
+          "editorMode": "code",
+          "expr": "{filename=\"/tmp/alloy-logs/tracing.log\"} | json | level = `TRACE` | line_format \"{{.fields_message}}\"",
+          "queryType": "range",
+          "refId": "A"
+        }
+      ],
+      "title": "Trace",
+      "type": "logs"
+    },
+    {
+      "datasource": {
+        "type": "loki",
+        "uid": "${DS_LOKI}"
+      },
+      "gridPos": {
+        "h": 8,
+        "w": 12,
+        "x": 0,
+        "y": 34
+      },
+      "id": 3,
+      "options": {
+        "dedupStrategy": "none",
+        "enableLogDetails": true,
+        "prettifyLogMessage": false,
+        "showCommonLabels": false,
+        "showLabels": false,
+        "showTime": false,
+        "sortOrder": "Descending",
+        "wrapLogMessage": false
+      },
+      "pluginVersion": "11.3.1",
+      "targets": [
+        {
+          "datasource": {
+            "type": "loki",
+            "uid": "${DS_LOKI}"
+          },
+          "editorMode": "code",
+          "expr": "{filename=\"/tmp/alloy-logs/tracing.log\"} | json | level = `WARN` | line_format \"{{.fields_message}}\"",
+          "queryType": "range",
+          "refId": "A"
+        }
+      ],
+      "title": "Warnings",
+      "type": "logs"
+    }
+  ],
+  "schemaVersion": 40,
+  "tags": [],
+  "templating": {
+    "list": [
+      {
+        "datasource": {
+          "type": "loki",
+          "uid": "P8E80F9AEF21F6940"
+        },
+        "filters": [],
+        "name": "Filters",
+        "type": "adhoc"
+      }
+    ]
+  },
+  "time": {
+    "from": "now-5m",
+    "to": "now"
+  },
+  "timepicker": {},
+  "timezone": "browser",
+  "title": "Crawler",
+  "uid": "ceg90x34pqgowd",
+  "version": 21,
+  "weekStart": ""
+}

docker/grafana.yaml

@@ -0,0 +1,41 @@
+apiVersion: 1
+
+datasources:
+- name: Loki
+  type: loki
+  access: proxy 
+  orgId: 1
+  url: http://loki:3100
+  basicAuth: false
+  isDefault: true 
+  version: 1
+  editable: false
+- name: Prometheus
+  type: prometheus
+  uid: prometheus
+  access: proxy
+  orgId: 1
+  url: http://prometheus:9090
+  basicAuth: false
+  isDefault: false
+  version: 1
+  editable: false
+  jsonData:
+    httpMethod: GET
+- name: Tempo
+  type: tempo
+  access: proxy
+  orgId: 1
+  url: http://tempo:3200
+  basicAuth: false
+  isDefault: false
+  version: 1
+  editable: true
+  apiVersion: 1
+  uid: tempo
+  jsonData:
+    httpMethod: GET
+    serviceMap:
+      datasourceUid: prometheus
+    streamingEnabled:
+      search: true

docker/loki.yaml

@@ -0,0 +1,62 @@
+# this is mostly the default config from grafana's website
+
+auth_enabled: false
+
+server:
+  http_listen_port: 3100
+  grpc_listen_port: 9096
+  log_level: info
+  grpc_server_max_concurrent_streams: 1000
+
+common:
+  instance_addr: 127.0.0.1
+  path_prefix: /tmp/loki
+  storage:
+    filesystem:
+      chunks_directory: /tmp/loki/chunks
+      rules_directory: /tmp/loki/rules
+  replication_factor: 1
+  ring:
+    kvstore:
+      store: inmemory
+
+query_range:
+  results_cache:
+    cache:
+      embedded_cache:
+        enabled: true
+        max_size_mb: 100
+
+limits_config:
+  metric_aggregation_enabled: true
+
+schema_config:
+  configs:
+    - from: 2020-10-24
+      store: tsdb
+      object_store: filesystem
+      schema: v13
+      index:
+        prefix: index_
+        period: 24h
+
+pattern_ingester:
+  enabled: true
+  metric_aggregation:
+    loki_address: localhost:3100
+
+frontend:
+  encoding: protobuf
+
+# By default, Loki will send anonymous, but uniquely-identifiable usage and configuration
+# analytics to Grafana Labs. These statistics are sent to https://stats.grafana.org/
+#
+# Statistics help us better understand how Loki is used, and they show us performance
+# levels for most users. This helps us prioritize features and documentation.
+# For more information on what's sent, look at
+# https://github.com/grafana/loki/blob/main/pkg/analytics/stats.go
+# Refer to the buildReport method to see what goes into a report.
+#
+# If you would like to disable reporting, uncomment the following lines:
+analytics:
+  reporting_enabled: false

docker/prometheus.yaml

@@ -0,0 +1,15 @@
+global:
+  scrape_interval: 60s 
+  query_log_file: /etc/prometheus/query.log
+
+scrape_configs:
+  # Crawler configs get pushed with OTLP
+#  - job_name: 'loki'
+#    static_configs:
+#      - targets: ['loki:3100']
+#  - job_name: 'prometheus'
+#    static_configs:
+#      - targets: ['localhost:9090']
+  - job_name: 'tempo'
+    static_configs:
+      - targets: ['tempo:3200']

docker/tempo.yaml

@@ -0,0 +1,48 @@
+stream_over_http_enabled: true
+server:
+  http_listen_port: 3200
+  log_level: info
+
+query_frontend:
+  search:
+    duration_slo: 5s
+    throughput_bytes_slo: 1.073741824e+09
+    metadata_slo:
+      duration_slo: 5s
+      throughput_bytes_slo: 1.073741824e+09
+  trace_by_id:
+    duration_slo: 5s
+
+distributor:
+  receivers:
+    otlp:
+      protocols:
+        grpc:
+          endpoint: "tempo:4317"
+
+metrics_generator:
+  registry:
+    external_labels:
+      source: tempo
+      cluster: docker-compose
+  storage:
+    path: /var/tempo/generator/wal
+    remote_write:
+      - url: http://prometheus:9090/api/v1/write
+        send_exemplars: true
+  traces_storage:
+    path: /var/tempo/generator/traces
+
+storage:
+  trace:
+    backend: local # backend configuration to use
+    wal:
+      path: /var/tempo/wal # where to store the wal locally
+    local:
+      path: /var/tempo/blocks
+
+overrides:
+  defaults:
+    metrics_generator:
+      processors: [service-graphs, span-metrics, local-blocks] # enables metrics generator
+      generate_native_histograms: both

driver.py

@@ -1,49 +0,0 @@
-from surrealdb import Surreal
-import fileinput
-import asyncio
-
-
-async def main():
-    async with Surreal("ws://localhost:8000/rpc") as db:
-
-        await db.signin({"user": "root", "pass": "root"})
-        await db.use("test", "test")
-
-        for line in fileinput.input():
-        # Testing
-        # for line in ["https://oliveratkinson.net;->;http://google.com"]:
-
-            urls = line.split(";->;")
-            ffrom = urls[0].strip()
-            to= urls[1].strip()
-
-            to_id = None
-            from_id = None
-
-            if (ffrom == to):
-                print('Site has self-reference, ignoring')
-                continue
-
-            # FROM
-            result = await db.query(f"SELECT id FROM website WHERE url='{ffrom}'")
-            if (len(result[0]['result']) > 0):
-                from_id = result[0]['result'][0]['id']
-                await db.query(f"UPDATE {from_id} MERGE {{ crawled: True }}")
-            else:
-                from_response = await db.create("website", { "url":ffrom, "crawled":True, } )
-                from_id = from_response[0]["id"]
-
-            # TO
-            result = await db.query(f"SELECT id FROM website WHERE url='{to}'")
-            if (len(result[0]['result']) < 1):
-                # Object doesn't exists yet
-                to_response = await db.create("website", { "url":to })
-                to_id = to_response[0]["id"]
-            else:
-                to_id = result[0]['result'][0]['id']
-
-            await db.query(f"RELATE {from_id} -> links_to -> {to_id}");
-
-if __name__ == "__main__":
-    asyncio.run(main())
-

jsconfig.json

@@ -0,0 +1,16 @@
+{
+    "compilerOptions": {
+        "module": "ESNext",
+        "moduleResolution": "Bundler",
+        "target": "ES2022",
+        "jsx": "react",
+        "allowImportingTsExtensions": true,
+        "strictNullChecks": true,
+        "strictFunctionTypes": true
+    },
+    "exclude": [
+        "node_modules",
+        "**/node_modules/*"
+    ],
+    "typeAcquisition": {"include": ["firefox-webext-browser"]}
+}

poetry.lock

@@ -1,370 +0,0 @@
-# This file is automatically @generated by Poetry 1.8.3 and should not be changed by hand.
-
-[[package]]
-name = "annotated-types"
-version = "0.7.0"
-description = "Reusable constraint types to use with typing.Annotated"
-optional = false
-python-versions = ">=3.8"
-files = [
-    {file = "annotated_types-0.7.0-py3-none-any.whl", hash = "sha256:1f02e8b43a8fbbc3f3e0d4f0f4bfc8131bcb4eebe8849b8e5c773f3a1c582a53"},
-    {file = "annotated_types-0.7.0.tar.gz", hash = "sha256:aff07c09a53a08bc8cfccb9c85b05f1aa9a2a6f23728d790723543408344ce89"},
-]
-
-[[package]]
-name = "anyio"
-version = "4.4.0"
-description = "High level compatibility layer for multiple asynchronous event loop implementations"
-optional = false
-python-versions = ">=3.8"
-files = [
-    {file = "anyio-4.4.0-py3-none-any.whl", hash = "sha256:c1b2d8f46a8a812513012e1107cb0e68c17159a7a594208005a57dc776e1bdc7"},
-    {file = "anyio-4.4.0.tar.gz", hash = "sha256:5aadc6a1bbb7cdb0bede386cac5e2940f5e2ff3aa20277e991cf028e0585ce94"},
-]
-
-[package.dependencies]
-exceptiongroup = {version = ">=1.0.2", markers = "python_version < \"3.11\""}
-idna = ">=2.8"
-sniffio = ">=1.1"
-typing-extensions = {version = ">=4.1", markers = "python_version < \"3.11\""}
-
-[package.extras]
-doc = ["Sphinx (>=7)", "packaging", "sphinx-autodoc-typehints (>=1.2.0)", "sphinx-rtd-theme"]
-test = ["anyio[trio]", "coverage[toml] (>=7)", "exceptiongroup (>=1.2.0)", "hypothesis (>=4.0)", "psutil (>=5.9)", "pytest (>=7.0)", "pytest-mock (>=3.6.1)", "trustme", "uvloop (>=0.17)"]
-trio = ["trio (>=0.23)"]
-
-[[package]]
-name = "certifi"
-version = "2024.7.4"
-description = "Python package for providing Mozilla's CA Bundle."
-optional = false
-python-versions = ">=3.6"
-files = [
-    {file = "certifi-2024.7.4-py3-none-any.whl", hash = "sha256:c198e21b1289c2ab85ee4e67bb4b4ef3ead0892059901a8d5b622f24a1101e90"},
-    {file = "certifi-2024.7.4.tar.gz", hash = "sha256:5a1e7645bc0ec61a09e26c36f6106dd4cf40c6db3a1fb6352b0244e7fb057c7b"},
-]
-
-[[package]]
-name = "exceptiongroup"
-version = "1.2.2"
-description = "Backport of PEP 654 (exception groups)"
-optional = false
-python-versions = ">=3.7"
-files = [
-    {file = "exceptiongroup-1.2.2-py3-none-any.whl", hash = "sha256:3111b9d131c238bec2f8f516e123e14ba243563fb135d3fe885990585aa7795b"},
-    {file = "exceptiongroup-1.2.2.tar.gz", hash = "sha256:47c2edf7c6738fafb49fd34290706d1a1a2f4d1c6df275526b62cbb4aa5393cc"},
-]
-
-[package.extras]
-test = ["pytest (>=6)"]
-
-[[package]]
-name = "h11"
-version = "0.14.0"
-description = "A pure-Python, bring-your-own-I/O implementation of HTTP/1.1"
-optional = false
-python-versions = ">=3.7"
-files = [
-    {file = "h11-0.14.0-py3-none-any.whl", hash = "sha256:e3fe4ac4b851c468cc8363d500db52c2ead036020723024a109d37346efaa761"},
-    {file = "h11-0.14.0.tar.gz", hash = "sha256:8f19fbbe99e72420ff35c00b27a34cb9937e902a8b810e2c88300c6f0a3b699d"},
-]
-
-[[package]]
-name = "httpcore"
-version = "1.0.5"
-description = "A minimal low-level HTTP client."
-optional = false
-python-versions = ">=3.8"
-files = [
-    {file = "httpcore-1.0.5-py3-none-any.whl", hash = "sha256:421f18bac248b25d310f3cacd198d55b8e6125c107797b609ff9b7a6ba7991b5"},
-    {file = "httpcore-1.0.5.tar.gz", hash = "sha256:34a38e2f9291467ee3b44e89dd52615370e152954ba21721378a87b2960f7a61"},
-]
-
-[package.dependencies]
-certifi = "*"
-h11 = ">=0.13,<0.15"
-
-[package.extras]
-asyncio = ["anyio (>=4.0,<5.0)"]
-http2 = ["h2 (>=3,<5)"]
-socks = ["socksio (==1.*)"]
-trio = ["trio (>=0.22.0,<0.26.0)"]
-
-[[package]]
-name = "httpx"
-version = "0.27.0"
-description = "The next generation HTTP client."
-optional = false
-python-versions = ">=3.8"
-files = [
-    {file = "httpx-0.27.0-py3-none-any.whl", hash = "sha256:71d5465162c13681bff01ad59b2cc68dd838ea1f10e51574bac27103f00c91a5"},
-    {file = "httpx-0.27.0.tar.gz", hash = "sha256:a0cb88a46f32dc874e04ee956e4c2764aba2aa228f650b06788ba6bda2962ab5"},
-]
-
-[package.dependencies]
-anyio = "*"
-certifi = "*"
-httpcore = "==1.*"
-idna = "*"
-sniffio = "*"
-
-[package.extras]
-brotli = ["brotli", "brotlicffi"]
-cli = ["click (==8.*)", "pygments (==2.*)", "rich (>=10,<14)"]
-http2 = ["h2 (>=3,<5)"]
-socks = ["socksio (==1.*)"]
-
-[[package]]
-name = "idna"
-version = "3.8"
-description = "Internationalized Domain Names in Applications (IDNA)"
-optional = false
-python-versions = ">=3.6"
-files = [
-    {file = "idna-3.8-py3-none-any.whl", hash = "sha256:050b4e5baadcd44d760cedbd2b8e639f2ff89bbc7a5730fcc662954303377aac"},
-    {file = "idna-3.8.tar.gz", hash = "sha256:d838c2c0ed6fced7693d5e8ab8e734d5f8fda53a039c0164afb0b82e771e3603"},
-]
-
-[[package]]
-name = "pydantic"
-version = "2.8.2"
-description = "Data validation using Python type hints"
-optional = false
-python-versions = ">=3.8"
-files = [
-    {file = "pydantic-2.8.2-py3-none-any.whl", hash = "sha256:73ee9fddd406dc318b885c7a2eab8a6472b68b8fb5ba8150949fc3db939f23c8"},
-    {file = "pydantic-2.8.2.tar.gz", hash = "sha256:6f62c13d067b0755ad1c21a34bdd06c0c12625a22b0fc09c6b149816604f7c2a"},
-]
-
-[package.dependencies]
-annotated-types = ">=0.4.0"
-pydantic-core = "2.20.1"
-typing-extensions = [
-    {version = ">=4.12.2", markers = "python_version >= \"3.13\""},
-    {version = ">=4.6.1", markers = "python_version < \"3.13\""},
-]
-
-[package.extras]
-email = ["email-validator (>=2.0.0)"]
-
-[[package]]
-name = "pydantic-core"
-version = "2.20.1"
-description = "Core functionality for Pydantic validation and serialization"
-optional = false
-python-versions = ">=3.8"
-files = [
-    {file = "pydantic_core-2.20.1-cp310-cp310-macosx_10_12_x86_64.whl", hash = "sha256:3acae97ffd19bf091c72df4d726d552c473f3576409b2a7ca36b2f535ffff4a3"},
-    {file = "pydantic_core-2.20.1-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:41f4c96227a67a013e7de5ff8f20fb496ce573893b7f4f2707d065907bffdbd6"},
-    {file = "pydantic_core-2.20.1-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5f239eb799a2081495ea659d8d4a43a8f42cd1fe9ff2e7e436295c38a10c286a"},
-    {file = "pydantic_core-2.20.1-cp310-cp310-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:53e431da3fc53360db73eedf6f7124d1076e1b4ee4276b36fb25514544ceb4a3"},
-    {file = "pydantic_core-2.20.1-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:f1f62b2413c3a0e846c3b838b2ecd6c7a19ec6793b2a522745b0869e37ab5bc1"},
-    {file = "pydantic_core-2.20.1-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:5d41e6daee2813ecceea8eda38062d69e280b39df793f5a942fa515b8ed67953"},
-    {file = "pydantic_core-2.20.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3d482efec8b7dc6bfaedc0f166b2ce349df0011f5d2f1f25537ced4cfc34fd98"},
-    {file = "pydantic_core-2.20.1-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:e93e1a4b4b33daed65d781a57a522ff153dcf748dee70b40c7258c5861e1768a"},
-    {file = "pydantic_core-2.20.1-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:e7c4ea22b6739b162c9ecaaa41d718dfad48a244909fe7ef4b54c0b530effc5a"},
-    {file = "pydantic_core-2.20.1-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:4f2790949cf385d985a31984907fecb3896999329103df4e4983a4a41e13e840"},
-    {file = "pydantic_core-2.20.1-cp310-none-win32.whl", hash = "sha256:5e999ba8dd90e93d57410c5e67ebb67ffcaadcea0ad973240fdfd3a135506250"},
-    {file = "pydantic_core-2.20.1-cp310-none-win_amd64.whl", hash = "sha256:512ecfbefef6dac7bc5eaaf46177b2de58cdf7acac8793fe033b24ece0b9566c"},
-    {file = "pydantic_core-2.20.1-cp311-cp311-macosx_10_12_x86_64.whl", hash = "sha256:d2a8fa9d6d6f891f3deec72f5cc668e6f66b188ab14bb1ab52422fe8e644f312"},
-    {file = "pydantic_core-2.20.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:175873691124f3d0da55aeea1d90660a6ea7a3cfea137c38afa0a5ffabe37b88"},
-    {file = "pydantic_core-2.20.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:37eee5b638f0e0dcd18d21f59b679686bbd18917b87db0193ae36f9c23c355fc"},
-    {file = "pydantic_core-2.20.1-cp311-cp311-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:25e9185e2d06c16ee438ed39bf62935ec436474a6ac4f9358524220f1b236e43"},
-    {file = "pydantic_core-2.20.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:150906b40ff188a3260cbee25380e7494ee85048584998c1e66df0c7a11c17a6"},
-    {file = "pydantic_core-2.20.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8ad4aeb3e9a97286573c03df758fc7627aecdd02f1da04516a86dc159bf70121"},
-    {file = "pydantic_core-2.20.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:d3f3ed29cd9f978c604708511a1f9c2fdcb6c38b9aae36a51905b8811ee5cbf1"},
-    {file = "pydantic_core-2.20.1-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:b0dae11d8f5ded51699c74d9548dcc5938e0804cc8298ec0aa0da95c21fff57b"},
-    {file = "pydantic_core-2.20.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:faa6b09ee09433b87992fb5a2859efd1c264ddc37280d2dd5db502126d0e7f27"},
-    {file = "pydantic_core-2.20.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:9dc1b507c12eb0481d071f3c1808f0529ad41dc415d0ca11f7ebfc666e66a18b"},
-    {file = "pydantic_core-2.20.1-cp311-none-win32.whl", hash = "sha256:fa2fddcb7107e0d1808086ca306dcade7df60a13a6c347a7acf1ec139aa6789a"},
-    {file = "pydantic_core-2.20.1-cp311-none-win_amd64.whl", hash = "sha256:40a783fb7ee353c50bd3853e626f15677ea527ae556429453685ae32280c19c2"},
-    {file = "pydantic_core-2.20.1-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:595ba5be69b35777474fa07f80fc260ea71255656191adb22a8c53aba4479231"},
-    {file = "pydantic_core-2.20.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:a4f55095ad087474999ee28d3398bae183a66be4823f753cd7d67dd0153427c9"},
-    {file = "pydantic_core-2.20.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f9aa05d09ecf4c75157197f27cdc9cfaeb7c5f15021c6373932bf3e124af029f"},
-    {file = "pydantic_core-2.20.1-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:e97fdf088d4b31ff4ba35db26d9cc472ac7ef4a2ff2badeabf8d727b3377fc52"},
-    {file = "pydantic_core-2.20.1-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:bc633a9fe1eb87e250b5c57d389cf28998e4292336926b0b6cdaee353f89a237"},
-    {file = "pydantic_core-2.20.1-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:d573faf8eb7e6b1cbbcb4f5b247c60ca8be39fe2c674495df0eb4318303137fe"},
-    {file = "pydantic_core-2.20.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:26dc97754b57d2fd00ac2b24dfa341abffc380b823211994c4efac7f13b9e90e"},
-    {file = "pydantic_core-2.20.1-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:33499e85e739a4b60c9dac710c20a08dc73cb3240c9a0e22325e671b27b70d24"},
-    {file = "pydantic_core-2.20.1-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:bebb4d6715c814597f85297c332297c6ce81e29436125ca59d1159b07f423eb1"},
-    {file = "pydantic_core-2.20.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:516d9227919612425c8ef1c9b869bbbee249bc91912c8aaffb66116c0b447ebd"},
-    {file = "pydantic_core-2.20.1-cp312-none-win32.whl", hash = "sha256:469f29f9093c9d834432034d33f5fe45699e664f12a13bf38c04967ce233d688"},
-    {file = "pydantic_core-2.20.1-cp312-none-win_amd64.whl", hash = "sha256:035ede2e16da7281041f0e626459bcae33ed998cca6a0a007a5ebb73414ac72d"},
-    {file = "pydantic_core-2.20.1-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:0827505a5c87e8aa285dc31e9ec7f4a17c81a813d45f70b1d9164e03a813a686"},
-    {file = "pydantic_core-2.20.1-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:19c0fa39fa154e7e0b7f82f88ef85faa2a4c23cc65aae2f5aea625e3c13c735a"},
-    {file = "pydantic_core-2.20.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4aa223cd1e36b642092c326d694d8bf59b71ddddc94cdb752bbbb1c5c91d833b"},
-    {file = "pydantic_core-2.20.1-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:c336a6d235522a62fef872c6295a42ecb0c4e1d0f1a3e500fe949415761b8a19"},
-    {file = "pydantic_core-2.20.1-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:7eb6a0587eded33aeefea9f916899d42b1799b7b14b8f8ff2753c0ac1741edac"},
-    {file = "pydantic_core-2.20.1-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:70c8daf4faca8da5a6d655f9af86faf6ec2e1768f4b8b9d0226c02f3d6209703"},
-    {file = "pydantic_core-2.20.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:e9fa4c9bf273ca41f940bceb86922a7667cd5bf90e95dbb157cbb8441008482c"},
-    {file = "pydantic_core-2.20.1-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:11b71d67b4725e7e2a9f6e9c0ac1239bbc0c48cce3dc59f98635efc57d6dac83"},
-    {file = "pydantic_core-2.20.1-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:270755f15174fb983890c49881e93f8f1b80f0b5e3a3cc1394a255706cabd203"},
-    {file = "pydantic_core-2.20.1-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:c81131869240e3e568916ef4c307f8b99583efaa60a8112ef27a366eefba8ef0"},
-    {file = "pydantic_core-2.20.1-cp313-none-win32.whl", hash = "sha256:b91ced227c41aa29c672814f50dbb05ec93536abf8f43cd14ec9521ea09afe4e"},
-    {file = "pydantic_core-2.20.1-cp313-none-win_amd64.whl", hash = "sha256:65db0f2eefcaad1a3950f498aabb4875c8890438bc80b19362cf633b87a8ab20"},
-    {file = "pydantic_core-2.20.1-cp38-cp38-macosx_10_12_x86_64.whl", hash = "sha256:4745f4ac52cc6686390c40eaa01d48b18997cb130833154801a442323cc78f91"},
-    {file = "pydantic_core-2.20.1-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:a8ad4c766d3f33ba8fd692f9aa297c9058970530a32c728a2c4bfd2616d3358b"},
-    {file = "pydantic_core-2.20.1-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:41e81317dd6a0127cabce83c0c9c3fbecceae981c8391e6f1dec88a77c8a569a"},
-    {file = "pydantic_core-2.20.1-cp38-cp38-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:04024d270cf63f586ad41fff13fde4311c4fc13ea74676962c876d9577bcc78f"},
-    {file = "pydantic_core-2.20.1-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:eaad4ff2de1c3823fddf82f41121bdf453d922e9a238642b1dedb33c4e4f98ad"},
-    {file = "pydantic_core-2.20.1-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:26ab812fa0c845df815e506be30337e2df27e88399b985d0bb4e3ecfe72df31c"},
-    {file = "pydantic_core-2.20.1-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3c5ebac750d9d5f2706654c638c041635c385596caf68f81342011ddfa1e5598"},
-    {file = "pydantic_core-2.20.1-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:2aafc5a503855ea5885559eae883978c9b6d8c8993d67766ee73d82e841300dd"},
-    {file = "pydantic_core-2.20.1-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:4868f6bd7c9d98904b748a2653031fc9c2f85b6237009d475b1008bfaeb0a5aa"},
-    {file = "pydantic_core-2.20.1-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:aa2f457b4af386254372dfa78a2eda2563680d982422641a85f271c859df1987"},
-    {file = "pydantic_core-2.20.1-cp38-none-win32.whl", hash = "sha256:225b67a1f6d602de0ce7f6c1c3ae89a4aa25d3de9be857999e9124f15dab486a"},
-    {file = "pydantic_core-2.20.1-cp38-none-win_amd64.whl", hash = "sha256:6b507132dcfc0dea440cce23ee2182c0ce7aba7054576efc65634f080dbe9434"},
-    {file = "pydantic_core-2.20.1-cp39-cp39-macosx_10_12_x86_64.whl", hash = "sha256:b03f7941783b4c4a26051846dea594628b38f6940a2fdc0df00b221aed39314c"},
-    {file = "pydantic_core-2.20.1-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:1eedfeb6089ed3fad42e81a67755846ad4dcc14d73698c120a82e4ccf0f1f9f6"},
-    {file = "pydantic_core-2.20.1-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:635fee4e041ab9c479e31edda27fcf966ea9614fff1317e280d99eb3e5ab6fe2"},
-    {file = "pydantic_core-2.20.1-cp39-cp39-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:77bf3ac639c1ff567ae3b47f8d4cc3dc20f9966a2a6dd2311dcc055d3d04fb8a"},
-    {file = "pydantic_core-2.20.1-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:7ed1b0132f24beeec5a78b67d9388656d03e6a7c837394f99257e2d55b461611"},
-    {file = "pydantic_core-2.20.1-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c6514f963b023aeee506678a1cf821fe31159b925c4b76fe2afa94cc70b3222b"},
-    {file = "pydantic_core-2.20.1-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:10d4204d8ca33146e761c79f83cc861df20e7ae9f6487ca290a97702daf56006"},
-    {file = "pydantic_core-2.20.1-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:2d036c7187b9422ae5b262badb87a20a49eb6c5238b2004e96d4da1231badef1"},
-    {file = "pydantic_core-2.20.1-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:9ebfef07dbe1d93efb94b4700f2d278494e9162565a54f124c404a5656d7ff09"},
-    {file = "pydantic_core-2.20.1-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:6b9d9bb600328a1ce523ab4f454859e9d439150abb0906c5a1983c146580ebab"},
-    {file = "pydantic_core-2.20.1-cp39-none-win32.whl", hash = "sha256:784c1214cb6dd1e3b15dd8b91b9a53852aed16671cc3fbe4786f4f1db07089e2"},
-    {file = "pydantic_core-2.20.1-cp39-none-win_amd64.whl", hash = "sha256:d2fe69c5434391727efa54b47a1e7986bb0186e72a41b203df8f5b0a19a4f669"},
-    {file = "pydantic_core-2.20.1-pp310-pypy310_pp73-macosx_10_12_x86_64.whl", hash = "sha256:a45f84b09ac9c3d35dfcf6a27fd0634d30d183205230a0ebe8373a0e8cfa0906"},
-    {file = "pydantic_core-2.20.1-pp310-pypy310_pp73-macosx_11_0_arm64.whl", hash = "sha256:d02a72df14dfdbaf228424573a07af10637bd490f0901cee872c4f434a735b94"},
-    {file = "pydantic_core-2.20.1-pp310-pypy310_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d2b27e6af28f07e2f195552b37d7d66b150adbaa39a6d327766ffd695799780f"},
-    {file = "pydantic_core-2.20.1-pp310-pypy310_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:084659fac3c83fd674596612aeff6041a18402f1e1bc19ca39e417d554468482"},
-    {file = "pydantic_core-2.20.1-pp310-pypy310_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:242b8feb3c493ab78be289c034a1f659e8826e2233786e36f2893a950a719bb6"},
-    {file = "pydantic_core-2.20.1-pp310-pypy310_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:38cf1c40a921d05c5edc61a785c0ddb4bed67827069f535d794ce6bcded919fc"},
-    {file = "pydantic_core-2.20.1-pp310-pypy310_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:e0bbdd76ce9aa5d4209d65f2b27fc6e5ef1312ae6c5333c26db3f5ade53a1e99"},
-    {file = "pydantic_core-2.20.1-pp310-pypy310_pp73-win_amd64.whl", hash = "sha256:254ec27fdb5b1ee60684f91683be95e5133c994cc54e86a0b0963afa25c8f8a6"},
-    {file = "pydantic_core-2.20.1-pp39-pypy39_pp73-macosx_10_12_x86_64.whl", hash = "sha256:407653af5617f0757261ae249d3fba09504d7a71ab36ac057c938572d1bc9331"},
-    {file = "pydantic_core-2.20.1-pp39-pypy39_pp73-macosx_11_0_arm64.whl", hash = "sha256:c693e916709c2465b02ca0ad7b387c4f8423d1db7b4649c551f27a529181c5ad"},
-    {file = "pydantic_core-2.20.1-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5b5ff4911aea936a47d9376fd3ab17e970cc543d1b68921886e7f64bd28308d1"},
-    {file = "pydantic_core-2.20.1-pp39-pypy39_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:177f55a886d74f1808763976ac4efd29b7ed15c69f4d838bbd74d9d09cf6fa86"},
-    {file = "pydantic_core-2.20.1-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:964faa8a861d2664f0c7ab0c181af0bea66098b1919439815ca8803ef136fc4e"},
-    {file = "pydantic_core-2.20.1-pp39-pypy39_pp73-musllinux_1_1_aarch64.whl", hash = "sha256:4dd484681c15e6b9a977c785a345d3e378d72678fd5f1f3c0509608da24f2ac0"},
-    {file = "pydantic_core-2.20.1-pp39-pypy39_pp73-musllinux_1_1_x86_64.whl", hash = "sha256:f6d6cff3538391e8486a431569b77921adfcdef14eb18fbf19b7c0a5294d4e6a"},
-    {file = "pydantic_core-2.20.1-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:a6d511cc297ff0883bc3708b465ff82d7560193169a8b93260f74ecb0a5e08a7"},
-    {file = "pydantic_core-2.20.1.tar.gz", hash = "sha256:26ca695eeee5f9f1aeeb211ffc12f10bcb6f71e2989988fda61dabd65db878d4"},
-]
-
-[package.dependencies]
-typing-extensions = ">=4.6.0,<4.7.0 || >4.7.0"
-
-[[package]]
-name = "sniffio"
-version = "1.3.1"
-description = "Sniff out which async library your code is running under"
-optional = false
-python-versions = ">=3.7"
-files = [
-    {file = "sniffio-1.3.1-py3-none-any.whl", hash = "sha256:2f6da418d1f1e0fddd844478f41680e794e6051915791a034ff65e5f100525a2"},
-    {file = "sniffio-1.3.1.tar.gz", hash = "sha256:f4324edc670a0f49750a81b895f35c3adb843cca46f0530f79fc1babb23789dc"},
-]
-
-[[package]]
-name = "surrealdb"
-version = "0.3.2"
-description = "The official SurrealDB library for Python."
-optional = false
-python-versions = ">=3.8,<4.0"
-files = [
-    {file = "surrealdb-0.3.2-py3-none-any.whl", hash = "sha256:30424971be9698f0fce61dc8387576d19302e0bb0ae708d311e79a261ead7701"},
-    {file = "surrealdb-0.3.2.tar.gz", hash = "sha256:8ab570b8d4299f35443f0d4fa636947cf1a18f67fd88acc00e5e5a36356e82cd"},
-]
-
-[package.dependencies]
-httpx = ">=0.23.0"
-pydantic = ">=2.1.0,<3.0.0"
-websockets = ">=10.4,<11.0"
-
-[[package]]
-name = "typing-extensions"
-version = "4.12.2"
-description = "Backported and Experimental Type Hints for Python 3.8+"
-optional = false
-python-versions = ">=3.8"
-files = [
-    {file = "typing_extensions-4.12.2-py3-none-any.whl", hash = "sha256:04e5ca0351e0f3f85c6853954072df659d0d13fac324d0072316b67d7794700d"},
-    {file = "typing_extensions-4.12.2.tar.gz", hash = "sha256:1a7ead55c7e559dd4dee8856e3a88b41225abfe1ce8df57b7c13915fe121ffb8"},
-]
-
-[[package]]
-name = "websockets"
-version = "10.4"
-description = "An implementation of the WebSocket Protocol (RFC 6455 & 7692)"
-optional = false
-python-versions = ">=3.7"
-files = [
-    {file = "websockets-10.4-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:d58804e996d7d2307173d56c297cf7bc132c52df27a3efaac5e8d43e36c21c48"},
-    {file = "websockets-10.4-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:bc0b82d728fe21a0d03e65f81980abbbcb13b5387f733a1a870672c5be26edab"},
-    {file = "websockets-10.4-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:ba089c499e1f4155d2a3c2a05d2878a3428cf321c848f2b5a45ce55f0d7d310c"},
-    {file = "websockets-10.4-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:33d69ca7612f0ddff3316b0c7b33ca180d464ecac2d115805c044bf0a3b0d032"},
-    {file = "websockets-10.4-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:62e627f6b6d4aed919a2052efc408da7a545c606268d5ab5bfab4432734b82b4"},
-    {file = "websockets-10.4-cp310-cp310-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:38ea7b82bfcae927eeffc55d2ffa31665dc7fec7b8dc654506b8e5a518eb4d50"},
-    {file = "websockets-10.4-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:e0cb5cc6ece6ffa75baccfd5c02cffe776f3f5c8bf486811f9d3ea3453676ce8"},
-    {file = "websockets-10.4-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:ae5e95cfb53ab1da62185e23b3130e11d64431179debac6dc3c6acf08760e9b1"},
-    {file = "websockets-10.4-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:7c584f366f46ba667cfa66020344886cf47088e79c9b9d39c84ce9ea98aaa331"},
-    {file = "websockets-10.4-cp310-cp310-win32.whl", hash = "sha256:b029fb2032ae4724d8ae8d4f6b363f2cc39e4c7b12454df8df7f0f563ed3e61a"},
-    {file = "websockets-10.4-cp310-cp310-win_amd64.whl", hash = "sha256:8dc96f64ae43dde92530775e9cb169979f414dcf5cff670455d81a6823b42089"},
-    {file = "websockets-10.4-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:47a2964021f2110116cc1125b3e6d87ab5ad16dea161949e7244ec583b905bb4"},
-    {file = "websockets-10.4-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:e789376b52c295c4946403bd0efecf27ab98f05319df4583d3c48e43c7342c2f"},
-    {file = "websockets-10.4-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:7d3f0b61c45c3fa9a349cf484962c559a8a1d80dae6977276df8fd1fa5e3cb8c"},
-    {file = "websockets-10.4-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f55b5905705725af31ccef50e55391621532cd64fbf0bc6f4bac935f0fccec46"},
-    {file = "websockets-10.4-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:00c870522cdb69cd625b93f002961ffb0c095394f06ba8c48f17eef7c1541f96"},
-    {file = "websockets-10.4-cp311-cp311-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8f38706e0b15d3c20ef6259fd4bc1700cd133b06c3c1bb108ffe3f8947be15fa"},
-    {file = "websockets-10.4-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:f2c38d588887a609191d30e902df2a32711f708abfd85d318ca9b367258cfd0c"},
-    {file = "websockets-10.4-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:fe10ddc59b304cb19a1bdf5bd0a7719cbbc9fbdd57ac80ed436b709fcf889106"},
-    {file = "websockets-10.4-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:90fcf8929836d4a0e964d799a58823547df5a5e9afa83081761630553be731f9"},
-    {file = "websockets-10.4-cp311-cp311-win32.whl", hash = "sha256:b9968694c5f467bf67ef97ae7ad4d56d14be2751000c1207d31bf3bb8860bae8"},
-    {file = "websockets-10.4-cp311-cp311-win_amd64.whl", hash = "sha256:a7a240d7a74bf8d5cb3bfe6be7f21697a28ec4b1a437607bae08ac7acf5b4882"},
-    {file = "websockets-10.4-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:74de2b894b47f1d21cbd0b37a5e2b2392ad95d17ae983e64727e18eb281fe7cb"},
-    {file = "websockets-10.4-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e3a686ecb4aa0d64ae60c9c9f1a7d5d46cab9bfb5d91a2d303d00e2cd4c4c5cc"},
-    {file = "websockets-10.4-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:b0d15c968ea7a65211e084f523151dbf8ae44634de03c801b8bd070b74e85033"},
-    {file = "websockets-10.4-cp37-cp37m-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:00213676a2e46b6ebf6045bc11d0f529d9120baa6f58d122b4021ad92adabd41"},
-    {file = "websockets-10.4-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:e23173580d740bf8822fd0379e4bf30aa1d5a92a4f252d34e893070c081050df"},
-    {file = "websockets-10.4-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:dd500e0a5e11969cdd3320935ca2ff1e936f2358f9c2e61f100a1660933320ea"},
-    {file = "websockets-10.4-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:4239b6027e3d66a89446908ff3027d2737afc1a375f8fd3eea630a4842ec9a0c"},
-    {file = "websockets-10.4-cp37-cp37m-win32.whl", hash = "sha256:8a5cc00546e0a701da4639aa0bbcb0ae2bb678c87f46da01ac2d789e1f2d2038"},
-    {file = "websockets-10.4-cp37-cp37m-win_amd64.whl", hash = "sha256:a9f9a735deaf9a0cadc2d8c50d1a5bcdbae8b6e539c6e08237bc4082d7c13f28"},
-    {file = "websockets-10.4-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:5c1289596042fad2cdceb05e1ebf7aadf9995c928e0da2b7a4e99494953b1b94"},
-    {file = "websockets-10.4-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:0cff816f51fb33c26d6e2b16b5c7d48eaa31dae5488ace6aae468b361f422b63"},
-    {file = "websockets-10.4-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:dd9becd5fe29773d140d68d607d66a38f60e31b86df75332703757ee645b6faf"},
-    {file = "websockets-10.4-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:45ec8e75b7dbc9539cbfafa570742fe4f676eb8b0d3694b67dabe2f2ceed8aa6"},
-    {file = "websockets-10.4-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4f72e5cd0f18f262f5da20efa9e241699e0cf3a766317a17392550c9ad7b37d8"},
-    {file = "websockets-10.4-cp38-cp38-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:185929b4808b36a79c65b7865783b87b6841e852ef5407a2fb0c03381092fa3b"},
-    {file = "websockets-10.4-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:7d27a7e34c313b3a7f91adcd05134315002aaf8540d7b4f90336beafaea6217c"},
-    {file = "websockets-10.4-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:884be66c76a444c59f801ac13f40c76f176f1bfa815ef5b8ed44321e74f1600b"},
-    {file = "websockets-10.4-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:931c039af54fc195fe6ad536fde4b0de04da9d5916e78e55405436348cfb0e56"},
-    {file = "websockets-10.4-cp38-cp38-win32.whl", hash = "sha256:db3c336f9eda2532ec0fd8ea49fef7a8df8f6c804cdf4f39e5c5c0d4a4ad9a7a"},
-    {file = "websockets-10.4-cp38-cp38-win_amd64.whl", hash = "sha256:48c08473563323f9c9debac781ecf66f94ad5a3680a38fe84dee5388cf5acaf6"},
-    {file = "websockets-10.4-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:40e826de3085721dabc7cf9bfd41682dadc02286d8cf149b3ad05bff89311e4f"},
-    {file = "websockets-10.4-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:56029457f219ade1f2fc12a6504ea61e14ee227a815531f9738e41203a429112"},
-    {file = "websockets-10.4-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:f5fc088b7a32f244c519a048c170f14cf2251b849ef0e20cbbb0fdf0fdaf556f"},
-    {file = "websockets-10.4-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:2fc8709c00704194213d45e455adc106ff9e87658297f72d544220e32029cd3d"},
-    {file = "websockets-10.4-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0154f7691e4fe6c2b2bc275b5701e8b158dae92a1ab229e2b940efe11905dff4"},
-    {file = "websockets-10.4-cp39-cp39-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4c6d2264f485f0b53adf22697ac11e261ce84805c232ed5dbe6b1bcb84b00ff0"},
-    {file = "websockets-10.4-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:9bc42e8402dc5e9905fb8b9649f57efcb2056693b7e88faa8fb029256ba9c68c"},
-    {file = "websockets-10.4-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:edc344de4dac1d89300a053ac973299e82d3db56330f3494905643bb68801269"},
-    {file = "websockets-10.4-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:84bc2a7d075f32f6ed98652db3a680a17a4edb21ca7f80fe42e38753a58ee02b"},
-    {file = "websockets-10.4-cp39-cp39-win32.whl", hash = "sha256:c94ae4faf2d09f7c81847c63843f84fe47bf6253c9d60b20f25edfd30fb12588"},
-    {file = "websockets-10.4-cp39-cp39-win_amd64.whl", hash = "sha256:bbccd847aa0c3a69b5f691a84d2341a4f8a629c6922558f2a70611305f902d74"},
-    {file = "websockets-10.4-pp37-pypy37_pp73-macosx_10_9_x86_64.whl", hash = "sha256:82ff5e1cae4e855147fd57a2863376ed7454134c2bf49ec604dfe71e446e2193"},
-    {file = "websockets-10.4-pp37-pypy37_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d210abe51b5da0ffdbf7b43eed0cfdff8a55a1ab17abbec4301c9ff077dd0342"},
-    {file = "websockets-10.4-pp37-pypy37_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:942de28af58f352a6f588bc72490ae0f4ccd6dfc2bd3de5945b882a078e4e179"},
-    {file = "websockets-10.4-pp37-pypy37_pp73-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:c9b27d6c1c6cd53dc93614967e9ce00ae7f864a2d9f99fe5ed86706e1ecbf485"},
-    {file = "websockets-10.4-pp37-pypy37_pp73-win_amd64.whl", hash = "sha256:3d3cac3e32b2c8414f4f87c1b2ab686fa6284a980ba283617404377cd448f631"},
-    {file = "websockets-10.4-pp38-pypy38_pp73-macosx_10_9_x86_64.whl", hash = "sha256:da39dd03d130162deb63da51f6e66ed73032ae62e74aaccc4236e30edccddbb0"},
-    {file = "websockets-10.4-pp38-pypy38_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:389f8dbb5c489e305fb113ca1b6bdcdaa130923f77485db5b189de343a179393"},
-    {file = "websockets-10.4-pp38-pypy38_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:09a1814bb15eff7069e51fed0826df0bc0702652b5cb8f87697d469d79c23576"},
-    {file = "websockets-10.4-pp38-pypy38_pp73-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:ff64a1d38d156d429404aaa84b27305e957fd10c30e5880d1765c9480bea490f"},
-    {file = "websockets-10.4-pp38-pypy38_pp73-win_amd64.whl", hash = "sha256:b343f521b047493dc4022dd338fc6db9d9282658862756b4f6fd0e996c1380e1"},
-    {file = "websockets-10.4-pp39-pypy39_pp73-macosx_10_9_x86_64.whl", hash = "sha256:932af322458da7e4e35df32f050389e13d3d96b09d274b22a7aa1808f292fee4"},
-    {file = "websockets-10.4-pp39-pypy39_pp73-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:d6a4162139374a49eb18ef5b2f4da1dd95c994588f5033d64e0bbfda4b6b6fcf"},
-    {file = "websockets-10.4-pp39-pypy39_pp73-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:c57e4c1349fbe0e446c9fa7b19ed2f8a4417233b6984277cce392819123142d3"},
-    {file = "websockets-10.4-pp39-pypy39_pp73-manylinux_2_5_x86_64.manylinux1_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b627c266f295de9dea86bd1112ed3d5fafb69a348af30a2422e16590a8ecba13"},
-    {file = "websockets-10.4-pp39-pypy39_pp73-win_amd64.whl", hash = "sha256:05a7233089f8bd355e8cbe127c2e8ca0b4ea55467861906b80d2ebc7db4d6b72"},
-    {file = "websockets-10.4.tar.gz", hash = "sha256:eef610b23933c54d5d921c92578ae5f89813438fded840c2e9809d378dc765d3"},
-]
-
-[metadata]
-lock-version = "2.0"
-python-versions = "^3.10"
-content-hash = "e5d2be363dd4d62589502cb214d66ac9f21992ad2fb62a09a50e243000600518"

pyproject.toml

@@ -1,15 +0,0 @@
-[tool.poetry]
-name = "surreal_spider"
-version = "0.1.0"
-description = ""
-authors = ["oliver <oliveratkinsoneng@gmail.com>"]
-
-[tool.poetry.dependencies]
-python = "^3.10"
-surrealdb = "^0.3.2"
-
-[tool.poetry.dev-dependencies]
-
-[build-system]
-requires = ["poetry-core>=1.0.0"]
-build-backend = "poetry.core.masonry.api"

schema.surql

@@ -1,15 +0,0 @@
-DELETE website;
-DELETE links_to;
-DELETE url_index;
-
-DEFINE TABLE website SCHEMAFULL;
-    DEFINE FIELD accessed_at ON TABLE website VALUE time::now();
-    DEFINE FIELD crawled     ON TABLE website TYPE bool DEFAULT false;
-    DEFINE FIELD url         ON TABLE website TYPE string;
-    DEFINE FIELD domain      ON TABLE website VALUE parse::url::domain($this.url) ASSERT !type::is::none($value);
-    DEFINE FIELD path        ON TABLE website VALUE parse::url::path($this.url) ASSERT !type::is::none($value);
-    DEFINE INDEX url_index   ON TABLE website COLUMNS url UNIQUE;
-
-DEFINE TABLE links_to SCHEMAFULL TYPE RELATION FROM website TO website;
-    DEFINE FIELD discovered_at ON TABLE links_to TYPE datetime DEFAULT time::now();
-

src/db.rs

@@ -0,0 +1,156 @@
+use metrics::counter;
+use serde::{Deserialize, Serialize};
+use std::{fmt::Debug, time::Duration};
+use surrealdb::{
+    engine::remote::ws::{Client, Ws},
+    opt::auth::Root,
+    sql::Thing,
+    Surreal,
+};
+use tokio::time::sleep;
+use tracing::{error, instrument, trace};
+use url::Url;
+
+use crate::Config;
+
+const STORE: &str = "surql_store_calls";
+
+#[derive(Serialize, Deserialize, Clone, Eq, PartialEq, Hash)]
+pub struct Website {
+    pub id: Option<Thing>,
+    /// The url that this data is found at
+    pub site: Url,
+    /// Wether or not this link has been crawled yet
+    pub crawled: bool,
+    /// 200, 404, etc
+    pub status_code: u16,
+}
+
+// manual impl to make tracing look nicer
+impl Debug for Website {
+    fn fmt(&self, f: &mut std::fmt::Formatter<'_>) -> std::fmt::Result {
+        f.debug_struct("Website")
+            .field("host", &self.site.host())
+            .field("path", &self.site.path())
+            .field("status_code", &self.status_code)
+            .finish()
+    }
+}
+
+impl Website {
+    /// Creates a blank site (assumes that url param is site's root)
+    pub fn new(url: &str, crawled: bool) -> Self {
+        let site = match Url::parse(url) {
+            Ok(a) => a,
+            Err(_) => todo!(),
+        };
+        Self {
+            crawled,
+            site,
+            status_code: 0,
+            id: None,
+        }
+    }
+
+    // Insert ever item in the vec into surreal, crawled state will be preserved as TRUE
+    // if already in the database as such or incoming data is TRUE.
+    #[instrument(skip(db))]
+    pub async fn store_all(all: Vec<Self>, db: &Surreal<Client>) -> Vec<Thing> {
+        counter!(STORE).increment(1);
+        let mut things = Vec::with_capacity(all.len());
+
+        match db
+            .query(
+                "INSERT INTO website $array
+                    ON DUPLICATE KEY UPDATE
+                        accessed_at = time::now(),
+                        status_code = $input.status_code,
+                        processing = false,
+                        crawled = crawled OR $input.crawled
+                    RETURN VALUE id;
+                 ",
+            )
+            .bind(("array", all))
+            .await
+        {
+            Ok(mut id) => match id.take::<Vec<Thing>>(0) {
+                Ok(mut x) => things.append(&mut x),
+                Err(err) => error!("{:?}", err),
+            },
+            Err(err) => {
+                error!("{:?}", err);
+            }
+        }
+        things
+    }
+}
+
+/// Returns uncrawled links
+#[instrument(skip(db, config))]
+pub async fn get_next(db: &Surreal<Client>, config: &Config) -> Option<Website> {
+    let mut res: Option<Website> = None;
+    let mut fails = 0;
+
+    while res == None {
+        let mut response = db
+            .query("fn::get_next($format)")
+            .bind(("format", config.crawl_filter.to_string()))
+            .await
+            .expect("Hard-coded query failed..?");
+
+        res = match response.take(0) {
+            Ok(ok) => ok,
+            Err(_err) => {
+                // basically just CSMA/CA
+                let delay = rand::random_range(10..10_000);
+                sleep(Duration::from_millis(delay)).await;
+                fails += 1;
+                // Don't get stuck here forever, failing...
+                // (most I've seen is 1)
+                if fails > 5 {
+                    error!("Max attempts to get_next() reached... ({fails})");
+                    return None
+                }
+                None
+            }
+        };
+    }
+
+    res
+}
+
+#[derive(Debug, Serialize)]
+#[allow(dead_code)]
+pub struct Email {
+    pub email: String,
+    pub on: String,
+}
+
+#[instrument(skip_all, name = "SurrealDB")]
+pub async fn connect(config: &Config) -> surrealdb::Result<Surreal<Client>> {
+    trace!("Establishing connection to surreal...");
+    // Connect to the server
+    let db = Surreal::new::<Ws>(&config.surreal_url).await?;
+
+    trace!("Logging in...");
+    // Signin as a namespace, database, or root user
+    db.signin(Root {
+        username: &config.surreal_username,
+        password: &config.surreal_password,
+    })
+    .await?;
+
+    // Select a specific namespace / database
+    db.use_ns(&config.surreal_ns)
+        .use_db(&config.surreal_db)
+        .await?;
+
+    let setup = include_bytes!("setup.surql");
+    let init_commands = setup.iter().map(|c| *c as char).collect::<String>();
+
+    db.query(init_commands)
+        .await
+        .expect("Failed to setup surreal tables.");
+
+    Ok(db)
+}

src/filesystem.rs

@@ -0,0 +1,105 @@
+use std::{io::ErrorKind, path::PathBuf};
+
+use reqwest::header::HeaderValue;
+use tokio::fs;
+use tracing::{error, trace, warn};
+use url::Url;
+
+pub fn as_path(url: &Url, content_type: &HeaderValue) -> PathBuf {
+    // extract data from url to save it accurately
+    let mut url_path = PathBuf::from("./downloaded/".to_string() + url.domain().unwrap_or("UnknownDomain") + url.path());
+
+    if let Ok(header) = content_type.to_str() {
+        // text/html; charset=UTF-8; option=value
+        let ttype = if let Some((t, _)) = header.split_once(';') {
+            t
+        } else {
+            header
+        };
+
+        if let Some((ttype, subtype)) = ttype.split_once('/') {
+            trace!(url = url.to_string(), main_type = ttype, sub_type = subtype, "Found Content-Type to be: {ttype}/{subtype}");
+            // If the Content-Type header is "*/html" (most likely "text/html") and the path's
+            // extension is anything but html:
+            if subtype=="html" && !url_path.extension().is_some_and(|f| f=="html" || f=="htm" ) {
+                // time to slap a index.html to the end of that path there!
+                url_path = url_path.join("index.html");
+            }
+        }
+    } else {
+        warn!("Header: {:?} couldn't be parsed into a string!", content_type);
+    }
+    trace!(url = url.to_string(), path = &*url_path.to_string_lossy(), "Converted URL into path");
+
+    url_path
+}
+
+pub async fn check_file_length(file: &PathBuf) -> Option<u64> {
+    match tokio::fs::OpenOptions::new()
+        .write(false)
+        .read(true)
+        .create(false)
+        .open(file).await
+    {
+        Ok(file) => {
+            match file.metadata().await {
+                Ok(meta) => {
+                    return Some(meta.len())
+                },
+                Err(err) => {
+                    error!("Failed to get metadata. {}", err)
+                },
+            }
+        },
+        Err(err) => {
+            match err.kind() {
+                ErrorKind::NotFound => {/* ignore */},
+                _ => warn!("Failed to open file to check length. {:?} {}", file, err),
+            }
+        },
+    }
+    None
+
+}
+
+pub async fn init(filename: &PathBuf) -> Option<fs::File> {
+    let file = async || tokio::fs::OpenOptions::new()
+        .write(true)
+        .append(false)
+        .create(true)
+        .open(&filename).await;
+
+    match file().await {
+        Ok(ok) => {
+            trace!("Initialized file {}", filename.to_str().unwrap_or("N/A"));
+            Some(ok)
+        },
+        Err(err) => {
+            // the file/folder isn't found
+            if err.kind() == ErrorKind::NotFound {
+                if let Some(parent ) = &filename.parent() {
+                    // create the folders
+                    if let Err(err) = fs::create_dir_all(&parent).await {
+                        error!("Dir creation: {err} {:?}", filename);
+                    } else if let Ok(ok) = file().await {
+                        return Some(ok);
+                    }
+                } else {
+                    error!("Couldn't get file's parents: {:?}", &filename);
+                }
+            } else if err.kind() == ErrorKind::NotADirectory {
+                // Example:
+                // 1. example.com/user
+                // 2. example.com/user/post
+                // If file 1 exists it will prevent file 2 from existing
+                // FIXME
+
+                error!("One of the parent directories is actually a file...")
+            } else {
+                error!("File open error: {err} {:?}", filename);
+            }
+            // we don't care about other errors, we can't/shouldn't fix them
+            None
+        }
+    }
+}

src/main.rs

@@ -1,35 +1,415 @@
-use spider::{hashbrown::HashMap, tokio};
+#![feature(ip_from)]
+#![feature(path_add_extension)]
+#![deny(clippy::unwrap_used)]
+
+extern crate html5ever;
+
+use std::{
+    collections::HashSet,
+    fs::File,
+    io::Read,
+    sync::{Arc, LazyLock},
+};
+
+use db::{connect, Website};
+use futures_util::StreamExt;
+use opentelemetry::{
+    global::{self},
+    metrics::{Counter, Meter, UpDownCounter},
+};
+use opentelemetry_otlp::{Protocol, WithExportConfig};
+use opentelemetry_sdk::{metrics::SdkMeterProvider, trace::SdkTracerProvider};
+use serde::Deserialize;
+use surrealdb::{engine::remote::ws::Client, Surreal};
+use tokio::{
+    io::{AsyncReadExt, AsyncWriteExt, BufWriter},
+    sync::RwLock,
+    task::JoinSet,
+};
+use tracing::{debug, error, info, instrument, level_filters::LevelFilter, trace, warn};
+use tracing_subscriber::{fmt, layer::SubscriberExt, EnvFilter, Layer, Registry};
+
+use crate::db::get_next;
+
+mod db;
+mod filesystem;
+mod parser;
+
+static METER: LazyLock<Meter> = LazyLock::new(|| global::meter("Internet_Mapper"));
+static BATCH_SIZE: LazyLock<Counter<u64>> =
+    LazyLock::new(|| METER.u64_counter("crawler_batch_size").build());
+static BEING_PROCESSED: LazyLock<UpDownCounter<i64>> = LazyLock::new(|| {
+    METER
+        .i64_up_down_counter("crawler_pages_being_processed")
+        .build()
+});
+static BEING_PARSED: LazyLock<UpDownCounter<i64>> = LazyLock::new(|| {
+    METER
+        .i64_up_down_counter("crawler_pages_being_parsed")
+        .build()
+});
+static BEING_STREAMED: LazyLock<UpDownCounter<i64>> = LazyLock::new(|| {
+    METER
+        .i64_up_down_counter("crawler_pages_being_streamed")
+        .build()
+});
+static GET_IN_FLIGHT: LazyLock<UpDownCounter<i64>> =
+    LazyLock::new(|| METER.i64_up_down_counter("crawler_gets_in_flight").build());
+static TOTAL_BYTES_DOWN: LazyLock<Counter<u64>> =
+    LazyLock::new(|| METER.u64_counter("crawler_total_bytes_down").build());
+static SITES_CRAWLED: LazyLock<Counter<u64>> =
+    LazyLock::new(|| METER.u64_counter("crawler_total_sites_crawled").build());
+
+static CONFIG: LazyLock<Config> = LazyLock::new(|| {
+    let mut file = File::open("./Crawler.toml").expect("Failed to read Crawler.toml");
+    let mut buf = String::new();
+    let _ = file.read_to_string(&mut buf);
+
+    let config: Config = toml::from_str(&buf).expect("Failed to parse Crawler.toml");
+    config
+});
+
+// FIXME Traces aren't working on multiple threads, they block
+// static TRACER: LazyLock<BoxedTracer> = LazyLock::new(|| global::tracer("Internet_Mapper"));
+
+#[derive(Deserialize)]
+struct Config {
+    tracing_endpoint: String,
+    metrics_endpoint: String,
+    log_file: String,
+
+    surreal_ns: String,
+    surreal_db: String,
+    surreal_url: String,
+    surreal_username: String,
+    surreal_password: String,
+
+    crawl_filter: String,
+    start_url: String,
+    budget: usize,
+    batch_size: usize,
+}
 
 #[tokio::main]
 async fn main() {
+    println!("Logs and metrics are provided to the Grafana dashboard");
 
-    let args = std::env::args().collect::<Vec<String>>();
+    // Start TRACE / LOGGING / METRICS
+    load_logging(&CONFIG); // this seems to be working ok
+    global::set_tracer_provider(load_tracing(&CONFIG));
+    global::set_meter_provider(load_metrics(&CONFIG));
 
-    let url = &args[1];
+    BATCH_SIZE.add(CONFIG.batch_size as u64, &[]);
-    let budget = &args[2];
-    let budget = match budget.parse::<u32>() {
-        Ok(x) => x,
-        Err(_) => panic!("Second arg must be a int"),
-    };
 
+    // When getting uncrawled pages, name must contain this variable. "" will effectively get ignored.
+    // let crawl_filter = "en.wikipedia.org/";
+    // let budget = 50;
+    let crawled = Arc::new(RwLock::new(0));
 
-    let mut site = spider::website::Website::new(url)
+    let starting_url = &CONFIG.start_url;
-        .with_budget(Some(HashMap::from([
-            ("*", budget),
-        ])))
-        .with_tld(true)
-        .with_on_link_find_callback(Some(|from, to| {
-            let from = from.as_ref().to_string();
-            let to = to.as_ref().to_string();
 
-            let from = from.trim();
+    let db = connect(&CONFIG)
-            let to= to.trim();
+        .await
+        .expect("Failed to connect to surreal, aborting.");
 
-            println!("{from};->;{to}"); 
+    let reqwest = reqwest::Client::builder()
-        }))
+        // .use_rustls_tls()
+        .gzip(true)
         .build()
-        .unwrap();
+        .expect("Failed to build reqwest client.");
 
-    site.crawl().await;
+    // Kick off the whole machine - This Website object doesn't matter, it's just to allow for
+    // get() to work.
+    // let mut span = TRACER.start("Pre-Loop");
+    let site = Website::new(starting_url, false);
+    process(site, db.clone(), reqwest.clone()).await;
+    // span.end();
+
+    // let mut main_loop_span= TRACER.start("Main-Loop");
+    let mut futures = JoinSet::new();
+    for _ in 0..CONFIG.batch_size {
+        futures.spawn(process_single_thread(
+            &CONFIG,
+            db.clone(),
+            reqwest.clone(),
+            crawled.clone(),
+        ));
+    }
+
+    while let Some(_) = futures.join_next().await {
+        // Budget - Threads - This thread (1)
+        // Would roughly be the acceptable amount at which a thread should exit
+        if *(crawled.read().await) < CONFIG.budget - CONFIG.batch_size - 1 {
+            warn!("Thread terminated early, restarting");
+            futures.spawn(process_single_thread(
+                &CONFIG,
+                db.clone(),
+                reqwest.clone(),
+                crawled.clone(),
+            ));
+        }
+    }
+
+    futures.join_all().await;
+    // main_loop_span.end();
+
+    info!("Done");
 }
 
+async fn process_single_thread(
+    config: &Config,
+    db: Surreal<Client>,
+    reqwest: reqwest::Client,
+    crawled: Arc<RwLock<usize>>,
+) {
+    while *(crawled.read().await) < config.budget {
+        let uncrawled = get_next(&db.clone(), &config).await;
+        match uncrawled {
+            Some(site) => {
+                process(site, db.clone(), reqwest.clone()).await;
+                SITES_CRAWLED.add(1, &[]);
+                // Somehow this write doesn't hang on the while's read?
+                let mut c = crawled.write().await;
+                *c += 1;
+            }
+            None => {
+                warn!("fn::get_next() returned None");
+                return;
+            }
+        }
+    }
+}
+
+#[instrument(skip(db, reqwest))]
+/// Downloads and crawls and stores a webpage.
+/// It is acceptable to clone `db`, `reqwest`, and `s3` because they all use `Arc`s internally. - Noted by Oliver
+async fn process(mut site: Website, db: Surreal<Client>, reqwest: reqwest::Client) {
+    // METRICS
+    debug!(url = &site.site.as_str(), "Process: {}", &site.site);
+    BEING_PROCESSED.add(1, &[]);
+    // let mut process_span = TRACER.start("Process");
+
+    // Build the request
+    let request_builder = reqwest.get(site.site.to_string());
+
+    // Send the http request (get)
+    GET_IN_FLIGHT.add(1, &[]);
+    if let Ok(response) = request_builder.send().await {
+        let mut skip_download = false;
+
+        GET_IN_FLIGHT.add(-1, &[]);
+
+        let headers = response.headers();
+        let code = response.status();
+        if code != 200 {
+            warn!("{code} for {}", site.site.as_str());
+        }
+
+        #[allow(non_snake_case)]
+        let CT = headers.get("Content-Type");
+        let ct = headers.get("content-type");
+
+        let ct = match (CT, ct) {
+            (None, None) => {
+                warn!(
+                    "Server did not respond with Content-Type header. Url: {} Headers: ({:?})",
+                    site.site.to_string(),
+                    headers
+                );
+                return;
+            }
+            (None, Some(a)) => a,
+            (Some(a), None) => a,
+            (Some(a), Some(_)) => a,
+        };
+
+        // create filepath (handles / -> /index.html)
+        let real_path = filesystem::as_path(&site.site, ct);
+        let mut tmp_path = real_path.clone();
+        if !(tmp_path.add_extension("crawl_temp")) {
+            warn!("Failed to add extension to file");
+            // fallback ig
+            tmp_path = tmp_path.with_extension("crawl_temp");
+        }
+
+        // CODE FOR UPDATING DOWNLOADED CONTENT:
+        // Check the Content-Length header (we assume the server is telling the truth) (I don't see
+        // a reason for it to lie in this case).
+        // And see if the file on the disk is the same length.
+        // Yes, technically this isn't perfect, but the other option is storing ETags, which I
+        // don't want to do right now.
+        if let Some(len) = headers.get("Content-Length") {
+            if let Ok(s) = len.to_str() {
+                // length is in bytes
+                if let Ok(len) = s.parse::<u64>() {
+                    if let Some(disk_len) = filesystem::check_file_length(&real_path).await {
+                        if disk_len == len {
+                            skip_download = true;
+                        }
+                    } else {
+                        // File not found (or other error).
+                        // Program will continue on it's way, downloading content.
+                    }
+                }
+            }
+        }
+
+        // make sure that the file is good to go
+        if let Some(file) = filesystem::init(&tmp_path).await {
+            // Get body from response
+            // stream the response onto the disk
+            let mut stream = response.bytes_stream();
+
+            let should_parse = real_path.to_string_lossy().ends_with(".html");
+
+            let mut buf: Vec<u8> = Vec::new();
+
+            if skip_download && should_parse {
+                // since we are skipping the download we will just read the file off the disk to
+                // parse it
+                if let Ok(mut file) = tokio::fs::OpenOptions::new() 
+                    .read(true)
+                    .open(&real_path).await
+                {
+                    if let Err(err) = file.read_to_end(&mut buf).await {
+                        warn!("Failed to read file off disk for parsing, {}", err);
+                    }
+                }
+            } 
+
+            // !!!DOWNLOADING TIME!!!
+            if !skip_download {
+                let mut writer = BufWriter::new(file);
+
+                // Write file to disk
+                trace!("Writing at: {:?}", tmp_path);
+                BEING_STREAMED.add(1, &[]);
+                // let mut stream_span = TRACER.start("Stream");
+                while let Some(data) = stream.next().await {
+                    match data {
+                        Ok(data) => {
+                            TOTAL_BYTES_DOWN.add(data.len() as u64, &[]);
+                            let _ = writer.write_all(&data).await;
+                            // If we are going to parse this file later, we will save it
+                            // into memory as well as the disk.
+                            // We do this because the data here might be incomplete
+                            if should_parse {
+                                data.iter().for_each(|f| buf.push(*f));
+                            }
+                        }
+                        Err(err) => {
+                            error!("{err}")
+                        }
+                    }
+                }
+                let _ = writer.flush().await;
+                // rename the temp file into the real file name
+                if let Err(err) = tokio::fs::rename(&tmp_path, &real_path).await {
+                    error!(
+                        from = &*tmp_path.to_string_lossy(),
+                        to = &*real_path.to_string_lossy(),
+                        "Error renaming file: {}",
+                        err
+                    );
+                }
+
+                // stream_span.end();
+                BEING_STREAMED.add(-1, &[]);
+            }
+
+            // (If needed) Parse the file
+            if should_parse {
+                BEING_PARSED.add(1, &[]);
+                // let mut parsing_span = TRACER.start("Parsing");
+
+                // Parse document and get relationships
+                let sites = parser::parse(&site, &buf).await;
+                // De-duplicate this list
+                let prev_len = sites.len();
+                let set = sites.into_iter().fold(HashSet::new(), |mut set, item| {
+                    set.insert(item);
+                    set
+                });
+                let de_dupe_sites: Vec<Website> = set.into_iter().collect();
+                let diff = prev_len - de_dupe_sites.len();
+                trace!("Saved {diff} from being entered into the db by de-duping");
+                // Store all the other sites so that we can link to them.
+                let _ = Website::store_all(de_dupe_sites, &db).await;
+
+                // parsing_span.end();
+                BEING_PARSED.add(-1, &[]);
+            } else {
+                trace!(url = site.site.as_str(), "Parse = False");
+            }
+
+            // update self in db
+            site.crawled = true;
+            site.status_code = code.as_u16();
+            Website::store_all(vec![site.clone()], &db).await;
+        }
+    } else {
+        error!(url = site.site.as_str(), "Failed to get: {}", &site.site);
+    }
+
+    // process_span.end();
+    BEING_PROCESSED.add(-1, &[]);
+}
+
+fn load_tracing(config: &Config) -> SdkTracerProvider {
+    // Send spans to Alloy (which will send them to Tempo)
+    let otlp_span = opentelemetry_otlp::SpanExporter::builder()
+        .with_tonic()
+        .with_endpoint(config.tracing_endpoint.clone())
+        .build()
+        .unwrap();
+    let tracer_provider = opentelemetry_sdk::trace::SdkTracerProvider::builder()
+        .with_simple_exporter(otlp_span)
+        .build();
+    tracer_provider
+}
+
+fn load_logging(config: &Config) {
+    //    let otlp_log = opentelemetry_otlp::LogExporter::builder()
+    //        .with_tonic()
+    //        .with_endpoint(endpoint)
+    //        .build()
+    //        .unwrap();
+    // let logger_provider = opentelemetry_sdk::logs::SdkLoggerProvider::builder()
+    //    .with_simple_exporter(otlp_log)
+    //    .build();
+    let writer = std::fs::OpenOptions::new()
+        .append(true)
+        .create(true)
+        .open(config.log_file.clone())
+        .expect("Couldn't make log file!");
+
+    let filter = EnvFilter::builder()
+        .with_default_directive(LevelFilter::DEBUG.into())
+        .from_env_lossy();
+
+    let registry = Registry::default().with(
+        fmt::layer()
+            .with_line_number(true)
+            .with_thread_ids(true)
+            .with_file(true)
+            .json()
+            .with_writer(writer)
+            .with_filter(filter),
+    );
+
+    tracing::subscriber::set_global_default(registry).expect("Failed to set default subscriber");
+}
+
+fn load_metrics(config: &Config) -> SdkMeterProvider {
+    //  Send metrics to Prometheus
+    let otlp_metrics = opentelemetry_otlp::MetricExporter::builder()
+        .with_http()
+        .with_protocol(Protocol::HttpBinary)
+        .with_endpoint(config.metrics_endpoint.clone())
+        .build()
+        .unwrap();
+    let metrics_provider = opentelemetry_sdk::metrics::SdkMeterProvider::builder()
+        .with_periodic_exporter(otlp_metrics) // default delay is 60s, turn down to like 15
+        .build();
+    metrics_provider
+}

src/parser.rs

@@ -0,0 +1,150 @@
+use std::default::Default;
+
+use html5ever::tokenizer::{BufferQueue, TokenizerResult};
+use html5ever::tokenizer::{StartTag, TagToken};
+use html5ever::tokenizer::{Token, TokenSink, TokenSinkResult, Tokenizer, TokenizerOpts};
+use html5ever::{local_name, tendril::*};
+use tracing::{error, instrument, trace, warn};
+use url::Url;
+
+use crate::db::Website;
+
+impl TokenSink for Website {
+    type Handle = Vec<Website>;
+
+    fn process_token(&self, token: Token, _line_number: u64) -> TokenSinkResult<Self::Handle> {
+        match token {
+            TagToken(tag) => {
+                if tag.kind == StartTag {
+                    match tag.name {
+                        // this should be all the html elements that have links
+                        local_name!("a")
+                        | local_name!("audio")
+                        | local_name!("area")
+                        | local_name!("img")
+                        | local_name!("link")
+                        | local_name!("object")
+                        | local_name!("source")
+                        | local_name!("base")
+                        | local_name!("video") => {
+                            let mut links = Vec::new();
+                            for attr in &tag.attrs {
+                                let attr_name = attr.name.local.to_string();
+                                if attr_name == "src" || attr_name == "href" || attr_name == "data"
+                                {
+                                    trace!(url = self.site.as_str(),"Found `{}` in html `{}` tag", &attr.value, tag.name);
+                                    let url = try_get_url(&self.site, &attr.value);
+
+                                    if let Some(mut parsed) = url {
+                                        parsed.set_query(None);
+                                        parsed.set_fragment(None);
+                                        trace!(url = self.site.as_str(), "Final cleaned URL: `{}`", parsed.to_string());
+                                        let web = Website::new(&parsed.to_string(), false);
+                                        links.push(web);
+                                    }
+                                }
+                            }
+                            return TokenSinkResult::Script(links);
+                        }
+                        local_name!("button") | local_name!("meta") | local_name!("iframe") => {
+                            // dbg!(attrs);
+                        }
+                        _ => {}
+                    }
+                }
+            }
+            _ => {}
+        }
+        TokenSinkResult::Continue
+    }
+}
+
+#[instrument(skip(data))]
+/// Parses the passed site and returns all the sites it links to.
+pub async fn parse(site: &Website, data: &[u8]) -> Vec<Website> {
+    trace!(url = site.site.as_str(), "Parsing {}", site.site.to_string());
+    // prep work
+    let mut other_sites: Vec<Website> = Vec::new();
+
+    // change data into something that can be tokenized
+    let s: Result<Tendril<fmt::UTF8>, ()> = Tendril::try_from_byte_slice(data);
+    if let Ok(chunk) = s {
+        // create buffer of tokens and push our input into it
+        let token_buffer = BufferQueue::default();
+        token_buffer.push_back(
+            chunk
+                .try_reinterpret::<fmt::UTF8>()
+                .expect("Failed to reinterpret chunk!"),
+        );
+        // create the tokenizer
+        let tokenizer = Tokenizer::new(site.clone(), TokenizerOpts::default());
+
+        // go thru buffer
+        while let TokenizerResult::Script(mut sites) = tokenizer.feed(&token_buffer) {
+            other_sites.append(&mut sites);
+            // other_sites.push(sites);
+        }
+        assert!(token_buffer.is_empty());
+        tokenizer.end();
+    } else {
+        warn!(url = site.site.as_str(), "Tendril failed to parse on: {}", site.site.to_string());
+    }
+
+    other_sites
+}
+
+#[instrument]
+fn try_get_url(parent: &Url, link: &str) -> Option<Url> {
+    match Url::parse(link) {
+        Ok(ok) => Some(ok),
+        Err(e) => {
+            if link.starts_with('#') {
+                trace!(url = parent.as_str(), "Rejecting # url");
+                None
+            } else if link.starts_with("//") {
+                // if a url starts with "//" is assumed that it will adopt
+                // the same scheme as it's parent
+                // https://stackoverflow.com/questions/9646407/two-forward-slashes-in-a-url-src-href-attribute
+                let scheme = parent.scheme();
+
+                match Url::parse(&format!("{scheme}://{link}")) {
+                    Ok(url) => Some(url),
+                    Err(err) => {
+                        error!("Failed parsing relative scheme url: {}", err);
+                        None
+                    }
+                }
+            } else {
+                // # This is some sort of relative url, gonna try patching it up into an absolute
+                // url
+                match e {
+                    url::ParseError::RelativeUrlWithoutBase => {
+                        // Is: scheme://host:port
+                        let mut origin = parent.origin().ascii_serialization();
+                        if !origin.ends_with('/') && !link.starts_with('/') {
+                            origin += "/";
+                        }
+                        let url = origin.clone() + link;
+
+                        if let Ok(url) = Url::parse(&url) {
+                            trace!(url = parent.as_str(), "Built `{url}` from `{origin} + `{}`", link.to_string());
+                            Some(url)
+                        } else {
+                            error!(
+                                "Failed to reconstruct a url from relative url: `{}` on site: `{}`. Failed url was: {}",
+                                link,
+                                parent.to_string(),
+                                url
+                            );
+                            None
+                        }
+                    }
+                    _ => {
+                        error!("MISC error: {:?} {:?}", e, link);
+                        None
+                    }
+                }
+            }
+        }
+    }
+}

src/setup.surql

@@ -0,0 +1,18 @@
+DEFINE TABLE IF NOT EXISTS website SCHEMALESS;
+
+DEFINE FIELD IF NOT EXISTS site ON TABLE website TYPE string;
+DEFINE INDEX IF NOT EXISTS idx ON TABLE website COLUMNS site UNIQUE;
+
+DEFINE FIELD IF NOT EXISTS crawled ON TABLE website TYPE bool;
+DEFINE FIELD IF NOT EXISTS processing ON TABLE website TYPE bool DEFAULT false;
+
+DEFINE FIELD IF NOT EXISTS accessed_at ON TABLE website VALUE time::now();
+DEFINE FIELD IF NOT EXISTS first_accessed_at ON TABLE website VALUE time::now();
+
+DEFINE FUNCTION OVERWRITE fn::get_next($filter: string) {
+    LET $site = SELECT * FROM ONLY website WHERE crawled = false AND processing = false AND site ~ type::string($filter) LIMIT 1;
+    UPDATE $site.id SET processing = true;
+    RETURN $site
+};
+
+UPDATE website SET processing = false WHERE processing = true;

test

@@ -1 +0,0 @@
-[{"result":[{"accessed_at":"2024-08-25T20:07:25.969525156Z","crawled":false,"domain":"google.com","id":"website:fd46b0cr5f5y3d57eje8","path":"/","url":"https://google.com"}],"status":"OK","time":"205.7