Spaces:

datenwerkzeuge
/

CDL-Webscraping-Workshop-2025

Sleeping

App Files Files Community

bsenst commited on Dec 31, 2024

Commit

c171b42

1 Parent(s): e392f4c

update youtube section

Browse files

Files changed (2) hide show

src/03_low_code/video_transcripts/get_videos_for_youtube_channels.ipynb +0 -0
src/03_low_code/video_transcripts/youtube-transcript-extraction.ipynb +49 -14

src/03_low_code/video_transcripts/get_videos_for_youtube_channels.ipynb CHANGED Viewed

The diff for this file is too large to render. See raw diff

src/03_low_code/video_transcripts/youtube-transcript-extraction.ipynb CHANGED Viewed

@@ -28,7 +28,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2024-12-08T19:21:41.981395Z",
@@ -39,9 +39,19 @@
     },
     "trusted": true
    },
-   "outputs": [],
    "source": [
-    "# ! pip install pytube youtube-transcript-api reportlab -q"
    ]
   },
   {
@@ -54,7 +64,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2024-12-08T19:21:56.471492Z",
@@ -85,7 +95,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2024-12-08T19:21:56.660152Z",
@@ -164,7 +174,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -231,7 +241,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2024-12-08T19:32:38.175946Z",
@@ -242,10 +252,27 @@
     },
     "trusted": true
    },
-   "outputs": [],
    "source": [
     "# Eingabe der URLs\n",
-    "urls = \"https://www.youtube.com/playlist?list=PLf8HAovJg47MN7bswKf73pffom98Fx8Q8\"\n",
     "\n",
     "pdf_filenames = []  # Liste zur Speicherung der PDF-Dateinamen\n",
     "\n",
@@ -263,7 +290,7 @@
     "    else:\n",
     "        video_urls = [url]\n",
     "\n",
-    "    for video_url in video_urls:\n",
     "        try:\n",
     "            yt = YouTube(video_url)\n",
     "            video_id = yt.video_id\n",
@@ -291,9 +318,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
    "metadata": {},
-   "outputs": [],
    "source": [
     "\n",
     "# Erstellen eines ZIP-Archivs\n",
@@ -316,7 +351,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2024-12-08T19:30:12.194584Z",
@@ -366,7 +401,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.10.14"
   }
  },
  "nbformat": 4,

   },
   {
    "cell_type": "code",
+   "execution_count": 18,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2024-12-08T19:21:41.981395Z",
     },
     "trusted": true
    },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m A new release of pip is available: \u001b[0m\u001b[31;49m24.2\u001b[0m\u001b[39;49m -> \u001b[0m\u001b[32;49m24.3.1\u001b[0m\n",
+      "\u001b[1m[\u001b[0m\u001b[34;49mnotice\u001b[0m\u001b[1;39;49m]\u001b[0m\u001b[39;49m To update, run: \u001b[0m\u001b[32;49mpython3 -m pip install --upgrade pip\u001b[0m\n"
+     ]
+    }
+   ],
    "source": [
+    "! pip install pytube youtube-transcript-api reportlab -q"
    ]
   },
   {
   },
   {
    "cell_type": "code",
+   "execution_count": 19,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2024-12-08T19:21:56.471492Z",
   },
   {
    "cell_type": "code",
+   "execution_count": 20,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2024-12-08T19:21:56.660152Z",
   },
   {
    "cell_type": "code",
+   "execution_count": 21,
    "metadata": {},
    "outputs": [],
    "source": [
   },
   {
    "cell_type": "code",
+   "execution_count": 22,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2024-12-08T19:32:38.175946Z",
     },
     "trusted": true
    },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Verarbeite Video: Jq7iHVGevRQ\n",
+      "Transkript für 'Jq7iHVGevRQ' gespeichert als Jq7iHVGevRQ.pdf.\n",
+      "Verarbeite Video: q9eWAtZxrW8\n",
+      "Transkript für 'q9eWAtZxrW8' gespeichert als q9eWAtZxrW8.pdf.\n",
+      "Verarbeite Video: NmjX3mkVTM4\n",
+      "Transkript für 'NmjX3mkVTM4' gespeichert als NmjX3mkVTM4.pdf.\n",
+      "Verarbeite Video: gELlAym0eJM\n",
+      "Transkript für 'gELlAym0eJM' gespeichert als gELlAym0eJM.pdf.\n",
+      "Verarbeite Video: qT2pbTlsNyk\n",
+      "Transkript für 'qT2pbTlsNyk' gespeichert als qT2pbTlsNyk.pdf.\n"
+     ]
+    }
+   ],
    "source": [
     "# Eingabe der URLs\n",
+    "urls = \"https://www.youtube.com/playlist?list=PLfRDp3S7rLduqUTa6oXe_Zlv7bEeD06t6\"\n",
     "\n",
     "pdf_filenames = []  # Liste zur Speicherung der PDF-Dateinamen\n",
     "\n",
     "    else:\n",
     "        video_urls = [url]\n",
     "\n",
+    "    for video_url in video_urls[:5]:\n",
     "        try:\n",
     "            yt = YouTube(video_url)\n",
     "            video_id = yt.video_id\n",
   },
   {
    "cell_type": "code",
+   "execution_count": 23,
    "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "ZIP-Archiv 'transcripts.zip' wurde erstellt.\n"
+     ]
+    }
+   ],
    "source": [
     "\n",
     "# Erstellen eines ZIP-Archivs\n",
   },
   {
    "cell_type": "code",
+   "execution_count": 24,
    "metadata": {
     "execution": {
      "iopub.execute_input": "2024-12-08T19:30:12.194584Z",
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
+   "version": "3.12.1"
   }
  },
  "nbformat": 4,