remove bash calls
Browse files
src/notebooks/Gesetze_im_Internet_Aktualitätendienst.ipynb
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
src/notebooks/quotes_scraper.ipynb
CHANGED
|
@@ -39,7 +39,7 @@
|
|
| 39 |
],
|
| 40 |
"source": [
|
| 41 |
"# Installieren der benötigten Bibliotheken\n",
|
| 42 |
-
"! pip install requests beautifulsoup4 pandas"
|
| 43 |
]
|
| 44 |
},
|
| 45 |
{
|
|
|
|
| 39 |
],
|
| 40 |
"source": [
|
| 41 |
"# Installieren der benötigten Bibliotheken\n",
|
| 42 |
+
"# ! pip install requests beautifulsoup4 pandas"
|
| 43 |
]
|
| 44 |
},
|
| 45 |
{
|
src/notebooks/youtube-transcript-extraction.ipynb
CHANGED
|
@@ -1 +1,290 @@
|
|
| 1 |
-
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cells": [
|
| 3 |
+
{
|
| 4 |
+
"cell_type": "code",
|
| 5 |
+
"execution_count": 1,
|
| 6 |
+
"metadata": {
|
| 7 |
+
"execution": {
|
| 8 |
+
"iopub.execute_input": "2024-12-08T19:21:41.981395Z",
|
| 9 |
+
"iopub.status.busy": "2024-12-08T19:21:41.981023Z",
|
| 10 |
+
"iopub.status.idle": "2024-12-08T19:21:56.468283Z",
|
| 11 |
+
"shell.execute_reply": "2024-12-08T19:21:56.466400Z",
|
| 12 |
+
"shell.execute_reply.started": "2024-12-08T19:21:41.981364Z"
|
| 13 |
+
},
|
| 14 |
+
"trusted": true
|
| 15 |
+
},
|
| 16 |
+
"outputs": [],
|
| 17 |
+
"source": [
|
| 18 |
+
"# ! pip install pytube youtube-transcript-api reportlab -q"
|
| 19 |
+
]
|
| 20 |
+
},
|
| 21 |
+
{
|
| 22 |
+
"cell_type": "code",
|
| 23 |
+
"execution_count": 2,
|
| 24 |
+
"metadata": {
|
| 25 |
+
"execution": {
|
| 26 |
+
"iopub.execute_input": "2024-12-08T19:21:56.471492Z",
|
| 27 |
+
"iopub.status.busy": "2024-12-08T19:21:56.470984Z",
|
| 28 |
+
"iopub.status.idle": "2024-12-08T19:21:56.658038Z",
|
| 29 |
+
"shell.execute_reply": "2024-12-08T19:21:56.656869Z",
|
| 30 |
+
"shell.execute_reply.started": "2024-12-08T19:21:56.471442Z"
|
| 31 |
+
},
|
| 32 |
+
"trusted": true
|
| 33 |
+
},
|
| 34 |
+
"outputs": [],
|
| 35 |
+
"source": [
|
| 36 |
+
"from pytube import YouTube, Playlist\n",
|
| 37 |
+
"from youtube_transcript_api import YouTubeTranscriptApi, TranscriptsDisabled, NoTranscriptFound\n",
|
| 38 |
+
"from reportlab.lib.pagesizes import letter\n",
|
| 39 |
+
"from reportlab.pdfgen import canvas\n",
|
| 40 |
+
"import os\n",
|
| 41 |
+
"import zipfile"
|
| 42 |
+
]
|
| 43 |
+
},
|
| 44 |
+
{
|
| 45 |
+
"cell_type": "code",
|
| 46 |
+
"execution_count": 3,
|
| 47 |
+
"metadata": {
|
| 48 |
+
"execution": {
|
| 49 |
+
"iopub.execute_input": "2024-12-08T19:21:56.660152Z",
|
| 50 |
+
"iopub.status.busy": "2024-12-08T19:21:56.659720Z",
|
| 51 |
+
"iopub.status.idle": "2024-12-08T19:21:56.675204Z",
|
| 52 |
+
"shell.execute_reply": "2024-12-08T19:21:56.674023Z",
|
| 53 |
+
"shell.execute_reply.started": "2024-12-08T19:21:56.660092Z"
|
| 54 |
+
},
|
| 55 |
+
"trusted": true
|
| 56 |
+
},
|
| 57 |
+
"outputs": [],
|
| 58 |
+
"source": [
|
| 59 |
+
"# Funktion zum Extrahieren des Transkripts\n",
|
| 60 |
+
"def get_transcript_with_language_preference(video_id, preferred_languages=(\"en\", \"de\"), prefer_manual=True):\n",
|
| 61 |
+
" \"\"\"\n",
|
| 62 |
+
" Extracts a transcript based on the preferred languages.\n",
|
| 63 |
+
" If no transcript is found in the preferred languages, it checks available languages.\n",
|
| 64 |
+
" \n",
|
| 65 |
+
" Args:\n",
|
| 66 |
+
" video_id (str): The ID of the YouTube video.\n",
|
| 67 |
+
" preferred_languages (tuple): Preferred languages in order of priority.\n",
|
| 68 |
+
" prefer_manual (bool): Whether to prefer manually created transcripts over auto-generated ones.\n",
|
| 69 |
+
" \n",
|
| 70 |
+
" Returns:\n",
|
| 71 |
+
" str: The transcript or an error message if not found.\n",
|
| 72 |
+
" \"\"\"\n",
|
| 73 |
+
" try:\n",
|
| 74 |
+
" # Fetch the transcript list for the video\n",
|
| 75 |
+
" transcript_list = YouTubeTranscriptApi.list_transcripts(video_id)\n",
|
| 76 |
+
" \n",
|
| 77 |
+
" # Filter transcripts for preferred languages and filter by manual or auto-generated type\n",
|
| 78 |
+
" transcript = None\n",
|
| 79 |
+
" for lang in preferred_languages:\n",
|
| 80 |
+
" try:\n",
|
| 81 |
+
" if prefer_manual:\n",
|
| 82 |
+
" transcript = transcript_list.find_transcript([lang]) # Prefer manually created transcripts\n",
|
| 83 |
+
" else:\n",
|
| 84 |
+
" transcript = transcript_list.find_transcript([lang], filter_types=['generated']) # Prefer auto-generated transcripts\n",
|
| 85 |
+
" \n",
|
| 86 |
+
" # If a valid transcript is found, break the loop\n",
|
| 87 |
+
" if transcript:\n",
|
| 88 |
+
" break\n",
|
| 89 |
+
" except Exception as e:\n",
|
| 90 |
+
" # Continue if no transcript found for this language\n",
|
| 91 |
+
" continue\n",
|
| 92 |
+
"\n",
|
| 93 |
+
" # If no transcript was found in the preferred languages, return available transcripts\n",
|
| 94 |
+
" if not transcript:\n",
|
| 95 |
+
" available_transcripts = transcript_list\n",
|
| 96 |
+
" available_languages = {t.language_code: t.language for t in available_transcripts}\n",
|
| 97 |
+
" \n",
|
| 98 |
+
" error_message = f\"Kein Transkript in den gewünschten Sprachen {preferred_languages} gefunden.\\n\"\n",
|
| 99 |
+
" error_message += \"Verfügbare Sprachen:\\n\"\n",
|
| 100 |
+
" error_message += \"\\n\".join([f\"- {code} ({lang})\" for code, lang in available_languages.items()])\n",
|
| 101 |
+
" return error_message\n",
|
| 102 |
+
"\n",
|
| 103 |
+
" # Get the actual transcript text\n",
|
| 104 |
+
" transcript_data = transcript.fetch()\n",
|
| 105 |
+
" return \"\\n\".join([entry[\"text\"] for entry in transcript_data])\n",
|
| 106 |
+
"\n",
|
| 107 |
+
" except TranscriptsDisabled:\n",
|
| 108 |
+
" return \"Transkripte sind für dieses Video deaktiviert.\"\n",
|
| 109 |
+
" except NoTranscriptFound:\n",
|
| 110 |
+
" return \"Es wurden keine Transkripte für dieses Video gefunden.\"\n",
|
| 111 |
+
" except Exception as e:\n",
|
| 112 |
+
" return f\"Allgemeiner Fehler beim Abrufen des Transkripts: {e}\"\n",
|
| 113 |
+
"\n",
|
| 114 |
+
"# Funktion zum Erstellen eines PDFs\n",
|
| 115 |
+
"def save_transcript_as_pdf_with_pagination(title, transcript):\n",
|
| 116 |
+
" \"\"\"\n",
|
| 117 |
+
" Speichert ein Transkript als PDF mit Seitenumbrüchen, wenn der Text zu lang ist.\n",
|
| 118 |
+
" Args:\n",
|
| 119 |
+
" title (str): Der Titel, der als Dateiname verwendet wird.\n",
|
| 120 |
+
" transcript (str): Der Text des Transkripts.\n",
|
| 121 |
+
" Returns:\n",
|
| 122 |
+
" str: Der Name der gespeicherten PDF-Datei.\n",
|
| 123 |
+
" \"\"\"\n",
|
| 124 |
+
" # Sicheren Dateinamen erstellen\n",
|
| 125 |
+
" filename = f\"{title}.pdf\".replace(\"/\", \"_\").replace(\"\\\\\", \"_\")\n",
|
| 126 |
+
"\n",
|
| 127 |
+
" # PDF-Einstellungen\n",
|
| 128 |
+
" c = canvas.Canvas(filename, pagesize=letter)\n",
|
| 129 |
+
" width, height = letter\n",
|
| 130 |
+
"\n",
|
| 131 |
+
" # Schrift- und Layout-Einstellungen\n",
|
| 132 |
+
" margin = 50\n",
|
| 133 |
+
" line_height = 14\n",
|
| 134 |
+
" max_lines_per_page = int((height - 2 * margin) / line_height) - 2 # Platz für Titel und Seitenrand\n",
|
| 135 |
+
"\n",
|
| 136 |
+
" # Titel schreiben\n",
|
| 137 |
+
" c.setFont(\"Helvetica-Bold\", 16)\n",
|
| 138 |
+
" c.drawString(margin, height - margin, title)\n",
|
| 139 |
+
"\n",
|
| 140 |
+
" # Textblock initialisieren\n",
|
| 141 |
+
" c.setFont(\"Helvetica\", 12)\n",
|
| 142 |
+
" y_position = height - margin - 30 # Platz für Titel\n",
|
| 143 |
+
"\n",
|
| 144 |
+
" # Text Zeile für Zeile schreiben\n",
|
| 145 |
+
" lines = transcript.split(\"\\n\")\n",
|
| 146 |
+
" line_count = 0\n",
|
| 147 |
+
"\n",
|
| 148 |
+
" for line in lines:\n",
|
| 149 |
+
" if line_count >= max_lines_per_page: # Neue Seite bei Bedarf\n",
|
| 150 |
+
" c.showPage()\n",
|
| 151 |
+
" c.setFont(\"Helvetica-Bold\", 16)\n",
|
| 152 |
+
" c.drawString(margin, height - margin, title)\n",
|
| 153 |
+
" c.setFont(\"Helvetica\", 12)\n",
|
| 154 |
+
" y_position = height - margin - 30\n",
|
| 155 |
+
" line_count = 0\n",
|
| 156 |
+
" \n",
|
| 157 |
+
" c.drawString(margin, y_position, line)\n",
|
| 158 |
+
" y_position -= line_height\n",
|
| 159 |
+
" line_count += 1\n",
|
| 160 |
+
"\n",
|
| 161 |
+
" # PDF speichern\n",
|
| 162 |
+
" c.save()\n",
|
| 163 |
+
" return filename"
|
| 164 |
+
]
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"cell_type": "code",
|
| 168 |
+
"execution_count": 15,
|
| 169 |
+
"metadata": {
|
| 170 |
+
"execution": {
|
| 171 |
+
"iopub.execute_input": "2024-12-08T19:32:38.175946Z",
|
| 172 |
+
"iopub.status.busy": "2024-12-08T19:32:38.175463Z",
|
| 173 |
+
"iopub.status.idle": "2024-12-08T19:32:40.711451Z",
|
| 174 |
+
"shell.execute_reply": "2024-12-08T19:32:40.710172Z",
|
| 175 |
+
"shell.execute_reply.started": "2024-12-08T19:32:38.175908Z"
|
| 176 |
+
},
|
| 177 |
+
"trusted": true
|
| 178 |
+
},
|
| 179 |
+
"outputs": [
|
| 180 |
+
{
|
| 181 |
+
"name": "stdout",
|
| 182 |
+
"output_type": "stream",
|
| 183 |
+
"text": [
|
| 184 |
+
"Verarbeite Video: B7uzC96-930\n",
|
| 185 |
+
"Transkript für 'B7uzC96-930' gespeichert als B7uzC96-930.pdf.\n",
|
| 186 |
+
"Verarbeite Video: 4QeKMnd8B7Q\n",
|
| 187 |
+
"Transkript für '4QeKMnd8B7Q' gespeichert als 4QeKMnd8B7Q.pdf.\n",
|
| 188 |
+
"Verarbeite Video: 30wxAJ5uyzs\n",
|
| 189 |
+
"Transkript für '30wxAJ5uyzs' gespeichert als 30wxAJ5uyzs.pdf.\n",
|
| 190 |
+
"ZIP-Archiv 'transcripts.zip' wurde erstellt.\n"
|
| 191 |
+
]
|
| 192 |
+
}
|
| 193 |
+
],
|
| 194 |
+
"source": [
|
| 195 |
+
"# Eingabe der URLs\n",
|
| 196 |
+
"urls = \"https://www.youtube.com/playlist?list=PLf8HAovJg47MN7bswKf73pffom98Fx8Q8\"\n",
|
| 197 |
+
"\n",
|
| 198 |
+
"pdf_filenames = [] # Liste zur Speicherung der PDF-Dateinamen\n",
|
| 199 |
+
"\n",
|
| 200 |
+
"# URL-Liste verarbeiten\n",
|
| 201 |
+
"url_list = urls.splitlines()\n",
|
| 202 |
+
"for url in url_list:\n",
|
| 203 |
+
" url = url.strip()\n",
|
| 204 |
+
" if not url:\n",
|
| 205 |
+
" continue\n",
|
| 206 |
+
"\n",
|
| 207 |
+
" # Playlist-URL oder Video-URL?\n",
|
| 208 |
+
" if \"playlist\" in url:\n",
|
| 209 |
+
" playlist = Playlist(url)\n",
|
| 210 |
+
" video_urls = playlist.video_urls\n",
|
| 211 |
+
" else:\n",
|
| 212 |
+
" video_urls = [url]\n",
|
| 213 |
+
"\n",
|
| 214 |
+
" for video_url in video_urls:\n",
|
| 215 |
+
" try:\n",
|
| 216 |
+
" yt = YouTube(video_url)\n",
|
| 217 |
+
" video_id = yt.video_id\n",
|
| 218 |
+
" title = video_id\n",
|
| 219 |
+
" print(f\"Verarbeite Video: {title}\")\n",
|
| 220 |
+
"\n",
|
| 221 |
+
" transcript = get_transcript_with_language_preference(video_id)\n",
|
| 222 |
+
"\n",
|
| 223 |
+
" # Speichern des Transkripts als PDF\n",
|
| 224 |
+
" pdf_filename = save_transcript_as_pdf_with_pagination(title, transcript)\n",
|
| 225 |
+
" pdf_filenames.append(pdf_filename)\n",
|
| 226 |
+
" print(f\"Transkript für '{title}' gespeichert als {pdf_filename}.\")\n",
|
| 227 |
+
"\n",
|
| 228 |
+
" except Exception as e:\n",
|
| 229 |
+
" print(f\"Fehler bei der Verarbeitung von {video_url}: {e}\")\n",
|
| 230 |
+
"\n",
|
| 231 |
+
"# Erstellen eines ZIP-Archivs\n",
|
| 232 |
+
"zip_filename = \"transcripts.zip\"\n",
|
| 233 |
+
"with zipfile.ZipFile(zip_filename, 'w') as zipf:\n",
|
| 234 |
+
" for pdf_filename in pdf_filenames:\n",
|
| 235 |
+
" zipf.write(pdf_filename)\n",
|
| 236 |
+
" os.remove(pdf_filename) # Lösche die PDF-Dateien nach dem Hinzufügen zum ZIP-Archiv\n",
|
| 237 |
+
"\n",
|
| 238 |
+
"print(f\"ZIP-Archiv '{zip_filename}' wurde erstellt.\")"
|
| 239 |
+
]
|
| 240 |
+
},
|
| 241 |
+
{
|
| 242 |
+
"cell_type": "code",
|
| 243 |
+
"execution_count": 13,
|
| 244 |
+
"metadata": {
|
| 245 |
+
"execution": {
|
| 246 |
+
"iopub.execute_input": "2024-12-08T19:30:12.194584Z",
|
| 247 |
+
"iopub.status.busy": "2024-12-08T19:30:12.194141Z",
|
| 248 |
+
"iopub.status.idle": "2024-12-08T19:30:12.200364Z",
|
| 249 |
+
"shell.execute_reply": "2024-12-08T19:30:12.198944Z",
|
| 250 |
+
"shell.execute_reply.started": "2024-12-08T19:30:12.194548Z"
|
| 251 |
+
},
|
| 252 |
+
"trusted": true
|
| 253 |
+
},
|
| 254 |
+
"outputs": [],
|
| 255 |
+
"source": [
|
| 256 |
+
"# os.remove(zip_filename)"
|
| 257 |
+
]
|
| 258 |
+
}
|
| 259 |
+
],
|
| 260 |
+
"metadata": {
|
| 261 |
+
"kaggle": {
|
| 262 |
+
"accelerator": "none",
|
| 263 |
+
"dataSources": [],
|
| 264 |
+
"dockerImageVersionId": 30804,
|
| 265 |
+
"isGpuEnabled": false,
|
| 266 |
+
"isInternetEnabled": true,
|
| 267 |
+
"language": "python",
|
| 268 |
+
"sourceType": "notebook"
|
| 269 |
+
},
|
| 270 |
+
"kernelspec": {
|
| 271 |
+
"display_name": "Python 3",
|
| 272 |
+
"language": "python",
|
| 273 |
+
"name": "python3"
|
| 274 |
+
},
|
| 275 |
+
"language_info": {
|
| 276 |
+
"codemirror_mode": {
|
| 277 |
+
"name": "ipython",
|
| 278 |
+
"version": 3
|
| 279 |
+
},
|
| 280 |
+
"file_extension": ".py",
|
| 281 |
+
"mimetype": "text/x-python",
|
| 282 |
+
"name": "python",
|
| 283 |
+
"nbconvert_exporter": "python",
|
| 284 |
+
"pygments_lexer": "ipython3",
|
| 285 |
+
"version": "3.10.14"
|
| 286 |
+
}
|
| 287 |
+
},
|
| 288 |
+
"nbformat": 4,
|
| 289 |
+
"nbformat_minor": 4
|
| 290 |
+
}
|