Add pypi 10k packages with most dependents dataset (#711)

From manual inspection, this dataset generated through the [libraries.io
API](https://libraries.io/api#project-search) seems more mainstream than
the current 8k one, which is also preserved. I've added the dataset to
the repo because the API requires an API key.

scripts/popular_packages/.gitignore

@@ -0,0 +1,2 @@
+pypi_8k_downloads.txt
+pypi_10k_most_dependents.txt

scripts/popular_packages/pypi_10k_most_dependents.ipynb

@@ -0,0 +1,86 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "initial_id",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "\"\"\"To update `pypi_10k_most_dependents.txt`, enter your `api_key` from https://libraries.io/account.\n",
+    "\n",
+    "The latest version is available at: https://gist.github.com/charliermarsh/07afd9f543dfea68408a4a42cede4be4.\n",
+    "\"\"\"\n",
+    "\n",
+    "import httpx\n",
+    "\n",
+    "from pathlib import Path\n",
+    "\n",
+    "api_key = \"\"\n",
+    "responses = {}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "d2532bf8c426af5",
+   "metadata": {
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
+   "outputs": [],
+   "source": [
+    "for i in range(100): # 100 pages with 100 per page -> 10k\n",
+    "    print(i)\n",
+    "    if not i in responses:\n",
+    "        # https://libraries.io/api#project-search\n",
+    "        sort = \"dependents_count\"\n",
+    "        url = f\"https://libraries.io/api/search?platforms=Pypi&per_page=100&page={i+1}&sort{sort}&api_key={api_key}\"\n",
+    "        responses[i] = httpx.get(url, timeout=30.0).json()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "7bc80702b6f8ebc3",
+   "metadata": {
+    "collapsed": false,
+    "jupyter": {
+     "outputs_hidden": false
+    }
+   },
+   "outputs": [],
+   "source": [
+    "flat_list = []\n",
+    "for response in responses.values():\n",
+    "    for entry in response:\n",
+    "        flat_list.append(entry[\"name\"])\n",
+    "print(flat_list)\n",
+    "Path().parent.joinpath(\"pypi_10k_most_dependents.txt\").write_text(\"\\n\".join(flat_list))"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 2
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython2",
+   "version": "2.7.6"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

scripts/popular_packages/pypi_8k_downloads.sh

@@ -1,4 +1,4 @@
 #!/usr/bin/env bash
 
-curl https://hugovk.github.io/top-pypi-packages/top-pypi-packages-30-days.min.json | jq -r ".rows | .[].project" > pypi_top_8k_flat.txt
+curl https://hugovk.github.io/top-pypi-packages/top-pypi-packages-30-days.min.json | jq -r ".rows | .[].project" > pypi_8k_downloads.txt
 

scripts/resolve/.gitignore

@@ -1 +0,0 @@
-pypi_top_8k_flat.txt