Move playlist tests to extractors.
From now on, test_download will run these tests. That means we benefit not only from the networking setup in there, but also from the other tests (for example test_all_urls to find problems with _VALID_URLs).
This commit is contained in:
Philipp Hagemeister
parent
259454525f
commit
22a6f15061
27 changed files with 345 additions and 449 deletions
|
|
@ -19,7 +19,7 @@ from ..utils import (
|
|||
class LivestreamIE(InfoExtractor):
|
||||
IE_NAME = 'livestream'
|
||||
_VALID_URL = r'http://new\.livestream\.com/.*?/(?P<event_name>.*?)(/videos/(?P<id>\d+))?/?$'
|
||||
_TEST = {
|
||||
_TESTS = [{
|
||||
'url': 'http://new.livestream.com/CoheedandCambria/WebsterHall/videos/4719370',
|
||||
'md5': '53274c76ba7754fb0e8d072716f2292b',
|
||||
'info_dict': {
|
||||
|
|
@ -31,7 +31,13 @@ class LivestreamIE(InfoExtractor):
|
|||
'view_count': int,
|
||||
'thumbnail': 're:^http://.*\.jpg$'
|
||||
}
|
||||
}
|
||||
}, {
|
||||
'url': 'http://new.livestream.com/tedx/cityenglish',
|
||||
'info_dict': {
|
||||
'title': 'TEDCity2.0 (English)',
|
||||
},
|
||||
'playlist_mincount': 4,
|
||||
}]
|
||||
|
||||
def _parse_smil(self, video_id, smil_url):
|
||||
formats = []
|
||||
|
|
@ -111,34 +117,37 @@ class LivestreamIE(InfoExtractor):
|
|||
event_name = mobj.group('event_name')
|
||||
webpage = self._download_webpage(url, video_id or event_name)
|
||||
|
||||
og_video = self._og_search_video_url(webpage, 'player url', fatal=False, default=None)
|
||||
if og_video is None:
|
||||
config_json = self._search_regex(
|
||||
r'window.config = ({.*?});', webpage, 'window config')
|
||||
info = json.loads(config_json)['event']
|
||||
|
||||
def is_relevant(vdata, vid):
|
||||
result = vdata['type'] == 'video'
|
||||
if video_id is not None:
|
||||
result = result and compat_str(vdata['data']['id']) == vid
|
||||
return result
|
||||
|
||||
videos = [self._extract_video_info(video_data['data'])
|
||||
for video_data in info['feed']['data']
|
||||
if is_relevant(video_data, video_id)]
|
||||
if video_id is None:
|
||||
# This is an event page:
|
||||
return self.playlist_result(videos, info['id'], info['full_name'])
|
||||
else:
|
||||
if videos:
|
||||
return videos[0]
|
||||
else:
|
||||
og_video = self._og_search_video_url(
|
||||
webpage, 'player url', fatal=False, default=None)
|
||||
if og_video is not None:
|
||||
query_str = compat_urllib_parse_urlparse(og_video).query
|
||||
query = compat_urlparse.parse_qs(query_str)
|
||||
api_url = query['play_url'][0].replace('.smil', '')
|
||||
info = json.loads(self._download_webpage(
|
||||
api_url, video_id, 'Downloading video info'))
|
||||
return self._extract_video_info(info)
|
||||
if 'play_url' in query:
|
||||
api_url = query['play_url'][0].replace('.smil', '')
|
||||
info = json.loads(self._download_webpage(
|
||||
api_url, video_id, 'Downloading video info'))
|
||||
return self._extract_video_info(info)
|
||||
|
||||
config_json = self._search_regex(
|
||||
r'window.config = ({.*?});', webpage, 'window config')
|
||||
info = json.loads(config_json)['event']
|
||||
|
||||
def is_relevant(vdata, vid):
|
||||
result = vdata['type'] == 'video'
|
||||
if video_id is not None:
|
||||
result = result and compat_str(vdata['data']['id']) == vid
|
||||
return result
|
||||
|
||||
videos = [self._extract_video_info(video_data['data'])
|
||||
for video_data in info['feed']['data']
|
||||
if is_relevant(video_data, video_id)]
|
||||
if video_id is None:
|
||||
# This is an event page:
|
||||
return self.playlist_result(videos, info['id'], info['full_name'])
|
||||
else:
|
||||
if not videos:
|
||||
raise ExtractorError('Cannot find video %s' % video_id)
|
||||
return videos[0]
|
||||
|
||||
|
||||
# The original version of Livestream uses a different system
|
||||
|
|
@ -148,7 +157,7 @@ class LivestreamOriginalIE(InfoExtractor):
|
|||
(?P<user>[^/]+)/(?P<type>video|folder)
|
||||
(?:\?.*?Id=|/)(?P<id>.*?)(&|$)
|
||||
'''
|
||||
_TEST = {
|
||||
_TESTS = [{
|
||||
'url': 'http://www.livestream.com/dealbook/video?clipId=pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
|
||||
'info_dict': {
|
||||
'id': 'pla_8aa4a3f1-ba15-46a4-893b-902210e138fb',
|
||||
|
|
@ -159,7 +168,13 @@ class LivestreamOriginalIE(InfoExtractor):
|
|||
# rtmp
|
||||
'skip_download': True,
|
||||
},
|
||||
}
|
||||
}, {
|
||||
'url': 'https://www.livestream.com/newplay/folder?dirId=a07bf706-d0e4-4e75-a747-b021d84f2fd3',
|
||||
'info_dict': {
|
||||
'id': 'a07bf706-d0e4-4e75-a747-b021d84f2fd3',
|
||||
},
|
||||
'playlist_mincount': 4,
|
||||
}]
|
||||
|
||||
def _extract_video(self, user, video_id):
|
||||
api_url = 'http://x{0}x.api.channel.livestream.com/2.0/clipdetails?extendedInfo=true&id={1}'.format(user, video_id)
|
||||
|
|
@ -182,15 +197,19 @@ class LivestreamOriginalIE(InfoExtractor):
|
|||
|
||||
def _extract_folder(self, url, folder_id):
|
||||
webpage = self._download_webpage(url, folder_id)
|
||||
urls = orderedSet(re.findall(r'<a href="(https?://livestre\.am/.*?)"', webpage))
|
||||
paths = orderedSet(re.findall(
|
||||
r'''(?x)(?:
|
||||
<li\s+class="folder">\s*<a\s+href="|
|
||||
<a\s+href="(?=https?://livestre\.am/)
|
||||
)([^"]+)"''', webpage))
|
||||
|
||||
return {
|
||||
'_type': 'playlist',
|
||||
'id': folder_id,
|
||||
'entries': [{
|
||||
'_type': 'url',
|
||||
'url': video_url,
|
||||
} for video_url in urls],
|
||||
'url': compat_urlparse.urljoin(url, p),
|
||||
} for p in paths],
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue