Download data for all packages on PyPI then slice into 8k files

.gitignore

@@ -99,3 +99,7 @@ ENV/
 
 # mypy
 .mypy_cache/
+
+# Big unzipped files
+top-pypi-packages-30-days-all.csv
+top-pypi-packages-30-days-all.json

.pre-commit-config.yaml

@@ -1,25 +1,39 @@
 repos:
+  - repo: https://github.com/astral-sh/ruff-pre-commit
+    rev: v0.8.0
+    hooks:
+      - id: ruff
+        args: [--exit-non-zero-on-fix]
+
+  - repo: https://github.com/psf/black-pre-commit-mirror
+    rev: 24.10.0
+    hooks:
+      - id: black
+
   - repo: https://github.com/pre-commit/pre-commit-hooks
     rev: v5.0.0
     hooks:
       - id: check-added-large-files
+        exclude: top-pypi-packages-30-days-all.*
       - id: check-case-conflict
       - id: check-merge-conflict
       - id: check-json
+      - id: check-toml
       - id: check-yaml
+      - id: debug-statements
       - id: end-of-file-fixer
       - id: forbid-submodules
       - id: trailing-whitespace
 
   - repo: https://github.com/python-jsonschema/check-jsonschema
-    rev: 0.29.3
+    rev: 0.29.4
     hooks:
       - id: check-github-workflows
 
-
   - repo: meta
     hooks:
       - id: check-hooks-apply
       - id: check-useless-excludes
+
 ci:
   autoupdate_schedule: quarterly

.ruff.toml

@@ -0,0 +1,29 @@
+fix = true
+
+lint.select = [
+  "C4",     # flake8-comprehensions
+  "E",      # pycodestyle
+  "EM",     # flake8-errmsg
+  "F",      # pyflakes
+  "I",      # isort
+  "ICN",    # flake8-import-conventions
+  "ISC",    # flake8-implicit-str-concat
+  "LOG",    # flake8-logging
+  "PGH",    # pygrep-hooks
+  "PT",     # flake8-pytest-style
+  "PYI",    # flake8-pyi
+  "RUF022", # unsorted-dunder-all
+  "RUF100", # unused noqa (yesqa)
+  "S",      # flake8-bandit
+  "UP",     # pyupgrade
+  "W",      # pycodestyle
+  "YTT",    # flake8-2020
+]
+lint.ignore = [
+  "E203",  # Whitespace before ':'
+  "E221",  # Multiple spaces before operator
+  "E226",  # Missing whitespace around arithmetic operator
+  "E241",  # Multiple spaces after ','
+  "UP038", # Makes code slower and more verbose
+]
+lint.isort.required-imports = [ "from __future__ import annotations" ]

README.md

@@ -18,12 +18,12 @@ Old versions can be found in [releases](https://github.com/hugovk/top-pypi-packa
 
 From cron, it runs pypinfo to dump JSON and commit back to this repo.
 
-### Install jq
+### Install jq and zip
 
 For example on Ubuntu 22.04:
 
 ```bash
-sudo apt-get install jq
+sudo apt-get install jq zip
 ```
 
 ### Install and set up pypinfo

build.sh

@@ -12,6 +12,10 @@ git pull origin main
 # Generate the files
 bash generate.sh
 
+# Remove big unzipped file
+rm top-pypi-packages-30-days-all.csv
+rm top-pypi-packages-30-days-all.json
+
 # Make output directory, don't fail if it exists
 # mkdir -p build
 

generate.sh

@@ -15,8 +15,20 @@ python3 -m pip install -U pypinfo
 python3 -m pip --version
 /home/botuser/.local/bin/pypinfo --version
 
+# Check if zip is installed
+if ! command -v zip &> /dev/null
+then
+    echo "zip not be found, consider: apt install zip"
+    exit 1
+fi
+
 # Generate and minify for 30 days
-/home/botuser/.local/bin/pypinfo --all --json --indent 0 --limit 8000 --days 30 "" project > top-pypi-packages-30-days.json
+/home/botuser/.local/bin/pypinfo --all --json --indent 0 --limit 10000000 --days 30 "" project > top-pypi-packages-30-days-all.json
+python3 trim.py > top-pypi-packages-30-days.json
 jq -c . < top-pypi-packages-30-days.json > top-pypi-packages-30-days.min.json
+echo 'download_count,project' > top-pypi-packages-30-days-all.csv
 echo 'download_count,project' > top-pypi-packages-30-days.csv
-jq -r '.rows[] | [.download_count, .project] | @csv' top-pypi-packages-30-days.json >> top-pypi-packages-30-days.csv
+jq -r '.rows[] | [.download_count, .project] | @csv' top-pypi-packages-30-days-all.json >> top-pypi-packages-30-days-all.csv
+jq -r '.rows[] | [.download_count, .project] | @csv' top-pypi-packages-30-days.json     >> top-pypi-packages-30-days.csv
+zip top-pypi-packages-30-days-all.csv.zip  top-pypi-packages-30-days-all.csv
+zip top-pypi-packages-30-days-all.json.zip top-pypi-packages-30-days-all.json

index.html

@@ -129,7 +129,8 @@ <h2 id="changelog">Changelog</h2>
           <li>2021-07: Fetch data for 5,000 packages over only 30 days (<a href="https://github.com/hugovk/top-pypi-packages/pull/20">#20</a>)</li>
           <li>2021-09: Fetch data for 8,000 packages (<a href="https://github.com/hugovk/top-pypi-packages/pull/30">#30</a>)</li>
           <li>2024-05: Provide data in CSV in addition to JSON (<a href="https://github.com/hugovk/top-pypi-packages/issues/31">#31</a>)</li>
-          <li>2024-11: Fetch data for all installers, not only pip (<a href="https://github.com/hugovk/top-pypi-packages/issues/39">#39</a>)</li>
+          <li>2024-11: Fetch data for all PyPI packages (<a href="https://github.com/hugovk/top-pypi-packages/issues/41">#41</a>)
+            and for installers, not only pip (<a href="https://github.com/hugovk/top-pypi-packages/issues/39">#39</a>)</li>
         </ul>
       </div>
       <div class="col-sm-6">