w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[airmozilla] Fix extraction (closes #12670)

Browse source
This commit is contained in:
Yen Chi Hsuan 2017-04-08 15:39:58 +08:00
parent 60e5016199
commit 4c03973296
No known key found for this signature in database
GPG key ID: 7F902A182457CA23
2 changed files with 16 additions and 18 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
ChangeLog
View file

@ -1,3 +1,9 @@
version <unreleased>
Extractors
* [airmozilla] Fix extraction (#12670)
version 2017.04.03 version 2017.04.03
Core Core

28
youtube_dl/extractor/airmozilla.py
View file

@ -15,12 +15,12 @@ class AirMozillaIE(InfoExtractor):
_VALID_URL = r'https?://air\.mozilla\.org/(?P<id>[0-9a-z-]+)/?' _VALID_URL = r'https?://air\.mozilla\.org/(?P<id>[0-9a-z-]+)/?'
_TEST = { _TEST = {
'url': 'https://air.mozilla.org/privacy-lab-a-meetup-for-privacy-minded-people-in-san-francisco/', 'url': 'https://air.mozilla.org/privacy-lab-a-meetup-for-privacy-minded-people-in-san-francisco/',
'md5': '2e3e7486ba5d180e829d453875b9b8bf', 'md5': '8d02f53ee39cf006009180e21df1f3ba',
'info_dict': { 'info_dict': {
'id': '6x4q2w', 'id': '6x4q2w',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Privacy Lab - a meetup for privacy minded people in San Francisco', 'title': 'Privacy Lab - a meetup for privacy minded people in San Francisco',
'thumbnail': r're:https?://vid\.ly/(?P<id>[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...', '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, 'timestamp': 1422487800,
'upload_date': '20150128', 'upload_date': '20150128',
@ -34,21 +34,13 @@ class AirMozillaIE(InfoExtractor):
def _real_extract(self, url): def _real_extract(self, url):
display_id = self._match_id(url) display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id) 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') jwconfig = self._parse_json(self._search_regex(
metadata = self._parse_json(jwconfig, video_id) r'initCallback\((.*)\);', embed_script, 'metadata'), video_id)['config']
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)
info_dict = self._parse_jwplayer_data(jwconfig, video_id)
view_count = int_or_none(self._html_search_regex( view_count = int_or_none(self._html_search_regex(
r'Views since archived: ([0-9]+)', r'Views since archived: ([0-9]+)',
webpage, 'view count', fatal=False)) webpage, 'view count', fatal=False))
@ -58,17 +50,17 @@ class AirMozillaIE(InfoExtractor):
r'Duration:\s*(\d+\s*hours?\s*\d+\s*minutes?)', r'Duration:\s*(\d+\s*hours?\s*\d+\s*minutes?)',
webpage, 'duration', fatal=False)) webpage, 'duration', fatal=False))
return { info_dict.update({
'id': video_id, 'id': video_id,
'title': self._og_search_title(webpage), 'title': self._og_search_title(webpage),
'formats': formats,
'url': self._og_search_url(webpage), 'url': self._og_search_url(webpage),
'display_id': display_id, 'display_id': display_id,
'thumbnail': metadata['playlist'][0].get('image'),
'description': self._og_search_description(webpage), 'description': self._og_search_description(webpage),
'timestamp': timestamp, 'timestamp': timestamp,
'location': self._html_search_regex(r'Location: (.*)', webpage, 'location', default=None), 'location': self._html_search_regex(r'Location: (.*)', webpage, 'location', default=None),
'duration': duration, 'duration': duration,
'view_count': view_count, 'view_count': view_count,
'categories': re.findall(r'<a href=".*?" class="channel">(.*?)</a>', webpage), 'categories': re.findall(r'<a href=".*?" class="channel">(.*?)</a>', webpage),
} })
return info_dict