From 4c0397329688144b8c0ec1d34227772fdfd03527 Mon Sep 17 00:00:00 2001 From: Yen Chi Hsuan Date: Sat, 8 Apr 2017 15:39:58 +0800 Subject: [PATCH] [airmozilla] Fix extraction (closes #12670) --- ChangeLog | 6 ++++++ youtube_dl/extractor/airmozilla.py | 28 ++++++++++------------------ 2 files changed, 16 insertions(+), 18 deletions(-) diff --git a/ChangeLog b/ChangeLog index 06a03bb9a..47804428f 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,3 +1,9 @@ +version + +Extractors +* [airmozilla] Fix extraction (#12670) + + version 2017.04.03 Core diff --git a/youtube_dl/extractor/airmozilla.py b/youtube_dl/extractor/airmozilla.py index 0e0691879..9e38136b4 100644 --- a/youtube_dl/extractor/airmozilla.py +++ b/youtube_dl/extractor/airmozilla.py @@ -15,12 +15,12 @@ class AirMozillaIE(InfoExtractor): _VALID_URL = r'https?://air\.mozilla\.org/(?P[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', - 'thumbnail': r're:https?://vid\.ly/(?P[0-9a-z-]+)/poster', + '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', @@ -34,21 +34,13 @@ class AirMozillaIE(InfoExtractor): 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) - 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)) @@ -58,17 +50,17 @@ def _real_extract(self, url): 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), - 'formats': formats, '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'(.*?)', webpage), - } + }) + + return info_dict