1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-24 18:30:43 +01:00

[discovery] Fix extractor

This commit is contained in:
Philipp Hagemeister 2015-01-08 17:36:56 +01:00
parent 740a7fcbc8
commit 9298d4e3df

View File

@ -1,47 +1,45 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import (
parse_iso8601,
int_or_none,
)
class DiscoveryIE(InfoExtractor): class DiscoveryIE(InfoExtractor):
_VALID_URL = r'http://www\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9\-]*)(.htm)?' _VALID_URL = r'http://www\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9_\-]*)(?:\.htm)?'
_TEST = { _TEST = {
'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm', 'url': 'http://www.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm',
'md5': 'e12614f9ee303a6ccef415cb0793eba2', 'md5': '3c69d77d9b0d82bfd5e5932a60f26504',
'info_dict': { 'info_dict': {
'id': '614784', 'id': 'mission-impossible-outtakes',
'ext': 'mp4', 'ext': 'flv',
'title': 'MythBusters: Mission Impossible Outtakes', 'title': 'Mission Impossible Outtakes',
'description': ('Watch Jamie Hyneman and Adam Savage practice being' 'description': ('Watch Jamie Hyneman and Adam Savage practice being'
' each other -- to the point of confusing Jamie\'s dog -- and ' ' each other -- to the point of confusing Jamie\'s dog -- and '
'don\'t miss Adam moon-walking as Jamie ... behind Jamie\'s' 'don\'t miss Adam moon-walking as Jamie ... behind Jamie\'s'
' back.'), ' back.'),
'duration': 156, 'duration': 156,
'timestamp': 1303099200,
'upload_date': '20110418',
}, },
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) video_id = self._match_id(url)
video_id = mobj.group('id')
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
video_list_json = self._search_regex(r'var videoListJSON = ({.*?});', info = self._parse_json(self._search_regex(
webpage, 'video list', flags=re.DOTALL) r'(?s)<script type="application/ld\+json">(.*?)</script>',
video_list = json.loads(video_list_json) webpage, 'video info'), video_id)
info = video_list['clips'][0]
formats = []
for f in info['mp4']:
formats.append(
{'url': f['src'], 'ext': 'mp4', 'tbr': int(f['bitrate'][:-1])})
return { return {
'id': info['contentId'], 'id': video_id,
'title': video_list['name'], 'title': info['name'],
'formats': formats, 'url': info['contentURL'],
'description': info['videoCaption'], 'description': info.get('description'),
'thumbnail': info.get('videoStillURL') or info.get('thumbnailURL'), 'thumbnail': info.get('thumbnailUrl'),
'duration': info['duration'], 'timestamp': parse_iso8601(info.get('uploadDate')),
'duration': int_or_none(info.get('duration')),
} }