Prepare to upload

[youtubedl] / youtube_dl / extractor / airmozilla.py

diff --git a/youtube_dl/extractor/airmozilla.py b/youtube_dl/extractor/airmozilla.py
index 611ad1e9d4a2c5892621802007b26c17e5802673..9e38136b4b795487659145ea81826eccdf4f341d 100644 (file)
--- a/youtube_dl/extractor/airmozilla.py
+++ b/youtube_dl/extractor/airmozilla.py
@@ -15,40 +15,32 @@ class AirMozillaIE(InfoExtractor):
     _VALID_URL = r'https?://air\.mozilla\.org/(?P<id>[0-9a-z-]+)/?'
     _TEST = {
         'url': 'https://air.mozilla.org/privacy-lab-a-meetup-for-privacy-minded-people-in-san-francisco/',
     _VALID_URL = r'https?://air\.mozilla\.org/(?P<id>[0-9a-z-]+)/?'
     _TEST = {
         'url': 'https://air.mozilla.org/privacy-lab-a-meetup-for-privacy-minded-people-in-san-francisco/',

-        'md5': '2e3e7486ba5d180e829d453875b9b8bf',
+        'md5': '8d02f53ee39cf006009180e21df1f3ba',

         'info_dict': {
             'id': '6x4q2w',
             'ext': 'mp4',
             'title': 'Privacy Lab - a meetup for privacy minded people in San Francisco',
         'info_dict': {
             'id': '6x4q2w',
             'ext': 'mp4',
             'title': 'Privacy Lab - a meetup for privacy minded people in San Francisco',

-            'thumbnail': 're:https://\w+\.cloudfront\.net/6x4q2w/poster\.jpg\?t=\d+',
+            'thumbnail': r're:https?://.*/poster\.jpg',

             'description': 'Brings together privacy professionals and others interested in privacy at for-profits, non-profits, and NGOs in an effort to contribute to the state of the ecosystem...',
             'timestamp': 1422487800,
             'upload_date': '20150128',
             'location': 'SFO Commons',
             'duration': 3780,
             'view_count': int,
             'description': 'Brings together privacy professionals and others interested in privacy at for-profits, non-profits, and NGOs in an effort to contribute to the state of the ecosystem...',
             'timestamp': 1422487800,
             'upload_date': '20150128',
             'location': 'SFO Commons',
             'duration': 3780,
             'view_count': int,

-            'categories': ['Main'],
+            'categories': ['Main', 'Privacy'],

         }
     }
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)
         }
     }
 
     def _real_extract(self, url):
         display_id = self._match_id(url)
         webpage = self._download_webpage(url, display_id)

-        video_id = self._html_search_regex(r'//vid.ly/(.*?)/embed', webpage, 'id')
+        video_id = self._html_search_regex(r'//vid\.ly/(.*?)/embed', webpage, 'id')

 
         embed_script = self._download_webpage('https://vid.ly/{0}/embed'.format(video_id), video_id)
 
         embed_script = self._download_webpage('https://vid.ly/{0}/embed'.format(video_id), video_id)

-        jwconfig = self._search_regex(r'\svar jwconfig = (\{.*?\});\s', embed_script, 'metadata')
-        metadata = self._parse_json(jwconfig, video_id)
-
-        formats = [{
-            'url': source['file'],
-            'ext': source['type'],
-            'format_id': self._search_regex(r'&format=(.*)$', source['file'], 'video format'),
-            'format': source['label'],
-            'height': int(source['label'].rstrip('p')),
-        } for source in metadata['playlist'][0]['sources']]
-        self._sort_formats(formats)
+        jwconfig = self._parse_json(self._search_regex(
+            r'initCallback\((.*)\);', embed_script, 'metadata'), video_id)['config']

 
 

+        info_dict = self._parse_jwplayer_data(jwconfig, video_id)

         view_count = int_or_none(self._html_search_regex(
             r'Views since archived: ([0-9]+)',
             webpage, 'view count', fatal=False))
         view_count = int_or_none(self._html_search_regex(
             r'Views since archived: ([0-9]+)',
             webpage, 'view count', fatal=False))


@@ -58,17 +50,17 @@ class AirMozillaIE(InfoExtractor):
             r'Duration:\s*(\d+\s*hours?\s*\d+\s*minutes?)',
             webpage, 'duration', fatal=False))
 
             r'Duration:\s*(\d+\s*hours?\s*\d+\s*minutes?)',
             webpage, 'duration', fatal=False))
 

-        return {
+        info_dict.update({

             'id': video_id,
             'title': self._og_search_title(webpage),
             'id': video_id,
             'title': self._og_search_title(webpage),

-            'formats': formats,

             'url': self._og_search_url(webpage),
             'display_id': display_id,
             'url': self._og_search_url(webpage),
             'display_id': display_id,

-            'thumbnail': metadata['playlist'][0].get('image'),

             'description': self._og_search_description(webpage),
             'timestamp': timestamp,
             'location': self._html_search_regex(r'Location: (.*)', webpage, 'location', default=None),
             'duration': duration,
             'view_count': view_count,
             'categories': re.findall(r'<a href=".*?" class="channel">(.*?)</a>', webpage),
             'description': self._og_search_description(webpage),
             'timestamp': timestamp,
             'location': self._html_search_regex(r'Location: (.*)', webpage, 'location', default=None),
             'duration': duration,
             'view_count': view_count,
             'categories': re.findall(r'<a href=".*?" class="channel">(.*?)</a>', webpage),

-        }
+        })
+
+        return info_dict