Merge changes from buster branch for the NMU while I was away.

[youtubedl] / youtube_dl / extractor / comcarcoff.py

diff --git a/youtube_dl/extractor/comcarcoff.py b/youtube_dl/extractor/comcarcoff.py
index 9c25b2223184ad1258b399b154aa821954581350..588aad0d911038229a4a3a97e5c74284f7bafc56 100644 (file)
--- a/youtube_dl/extractor/comcarcoff.py
+++ b/youtube_dl/extractor/comcarcoff.py
@@ -1,24 +1,27 @@
-# encoding: utf-8
+# coding: utf-8

 from __future__ import unicode_literals
 
 from __future__ import unicode_literals
 

-import json
-

 from .common import InfoExtractor
 from .common import InfoExtractor

-from ..utils import parse_iso8601
+from ..compat import compat_str
+from ..utils import (
+    int_or_none,
+    parse_duration,
+    parse_iso8601,
+)

 
 
 class ComCarCoffIE(InfoExtractor):
 
 
 class ComCarCoffIE(InfoExtractor):

-    _VALID_URL = r'http://(?:www\.)?comediansincarsgettingcoffee\.com/(?P<id>[a-z0-9\-]*)'
+    _VALID_URL = r'https?://(?:www\.)?comediansincarsgettingcoffee\.com/(?P<id>[a-z0-9\-]*)'

     _TESTS = [{
         'url': 'http://comediansincarsgettingcoffee.com/miranda-sings-happy-thanksgiving-miranda/',
         'info_dict': {
     _TESTS = [{
         'url': 'http://comediansincarsgettingcoffee.com/miranda-sings-happy-thanksgiving-miranda/',
         'info_dict': {

-            'id': 'miranda-sings-happy-thanksgiving-miranda',
+            'id': '2494164',

             'ext': 'mp4',
             'upload_date': '20141127',
             'timestamp': 1417107600,
             'ext': 'mp4',
             'upload_date': '20141127',
             'timestamp': 1417107600,

+            'duration': 1232,

             'title': 'Happy Thanksgiving Miranda',
             'description': 'Jerry Seinfeld and his special guest Miranda Sings cruise around town in search of coffee, complaining and apologizing along the way.',
             'title': 'Happy Thanksgiving Miranda',
             'description': 'Jerry Seinfeld and his special guest Miranda Sings cruise around town in search of coffee, complaining and apologizing along the way.',

-            'thumbnail': 'http://ccc.crackle.com/images/s5e4_thumb.jpg',

         },
         'params': {
             'skip_download': 'requires ffmpeg',
         },
         'params': {
             'skip_download': 'requires ffmpeg',


@@ -31,27 +34,41 @@ class ComCarCoffIE(InfoExtractor):
             display_id = 'comediansincarsgettingcoffee.com'
         webpage = self._download_webpage(url, display_id)
 
             display_id = 'comediansincarsgettingcoffee.com'
         webpage = self._download_webpage(url, display_id)
 

-        full_data = json.loads(self._search_regex(
-            r'<script type="application/json" id="videoData">(?P<json>.+?)</script>',
-            webpage, 'full data json'))
+        full_data = self._parse_json(
+            self._search_regex(
+                r'window\.app\s*=\s*({.+?});\n', webpage, 'full data json'),
+            display_id)['videoData']
+
+        display_id = full_data['activeVideo']['video']
+        video_data = full_data.get('videos', {}).get(display_id) or full_data['singleshots'][display_id]
+
+        video_id = compat_str(video_data['mediaId'])
+        title = video_data['title']
+        formats = self._extract_m3u8_formats(
+            video_data['mediaUrl'], video_id, 'mp4')
+        self._sort_formats(formats)

 
 

-        video_id = full_data['activeVideo']['video']
-        video_data = full_data['videos'][video_id]

         thumbnails = [{
             'url': video_data['images']['thumb'],
         }, {
             'url': video_data['images']['poster'],
         }]
         thumbnails = [{
             'url': video_data['images']['thumb'],
         }, {
             'url': video_data['images']['poster'],
         }]

-        formats = self._extract_m3u8_formats(
-            video_data['mediaUrl'], video_id, ext='mp4')
+
+        timestamp = int_or_none(video_data.get('pubDateTime')) or parse_iso8601(
+            video_data.get('pubDate'))
+        duration = int_or_none(video_data.get('durationSeconds')) or parse_duration(
+            video_data.get('duration'))

 
         return {
             'id': video_id,
             'display_id': display_id,
 
         return {
             'id': video_id,
             'display_id': display_id,

-            'title': video_data['title'],
+            'title': title,

             'description': video_data.get('description'),
             'description': video_data.get('description'),

-            'timestamp': parse_iso8601(video_data.get('pubDate')),
+            'timestamp': timestamp,
+            'duration': duration,

             'thumbnails': thumbnails,
             'formats': formats,
             'thumbnails': thumbnails,
             'formats': formats,

+            'season_number': int_or_none(video_data.get('season')),
+            'episode_number': int_or_none(video_data.get('episode')),

             'webpage_url': 'http://comediansincarsgettingcoffee.com/%s' % (video_data.get('urlSlug', video_data.get('slug'))),
         }
             'webpage_url': 'http://comediansincarsgettingcoffee.com/%s' % (video_data.get('urlSlug', video_data.get('slug'))),
         }