R-yan/l1ving_youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[vier] Without login, fall back to extraction without metadata

Browse Source
This commit is contained in:
mrBliss 2017-05-09 15:32:57 +02:00
parent 5bd43a87d5
commit 624e220f11
1 changed files with 31 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

39
youtube_dl/extractor/vier.py
View File

@ -28,13 +28,14 @@ class VierIE(InfoExtractor):
# m3u8 download
'skip_download': True,
},
# 'skip': 'Requires account credentials',
}, {
'url': 'http://www.vijf.be/temptationisland/videos/zo-grappig-temptation-island-hosts-moeten-kiezen-tussen-onmogelijke-dilemmas/2561614',
'info_dict': {
'id': '2561614',
'display_id': 'zo-grappig-temptation-island-hosts-moeten-kiezen-tussen-onmogelijke-dilemmas',
'ext': 'mp4',
'title': 'ZO grappig: Temptation Island hosts moeten kiezen tussen onmogelijke dilemma\'s',
'title': 'EXTRA: Temptation Island hosts moeten kiezen tussen onmogelijke dilemma\'s',
'description': 'Het spel is simpel: Annelien Coorevits en Rick Brandsteder krijgen telkens 2 dilemma\'s voorgeschoteld en ze MOETEN een keuze maken.',
},
'params': {
@ -53,7 +54,21 @@ class VierIE(InfoExtractor):
'params': {
# m3u8 download
'skip_download': True,
}
},
'skip': 'Requires account credentials',
}, {
'url': 'http://www.vier.be/janigaat/videos/jani-gaat-naar-tokio-aflevering-4/2674839',
'info_dict': {
'id': '2674839',
'display_id': 'jani-gaat-naar-tokio-aflevering-4',
'ext': 'mp4',
'title': 'jani-gaat-naar-tokio-aflevering-4',
},
'params': {
# m3u8 download
'skip_download': True,
},
'expected_warnings': ['Log in to extract metadata'],
}, {
'url': 'http://www.vier.be/planb/videos/mieren-herders-van-de-bladluizen',
'only_matching': True,
@ -62,10 +77,14 @@ class VierIE(InfoExtractor):
'only_matching': True,
}]
def _real_initialize(self):
self._logged_in = False
def _login(self, site):
username, password = self._get_login_info()
if username is None or password is None:
self.raise_login_required()
self.logged_in = False
return
self._request_webpage(
'http://www.%s.be/user/login' % site,
@ -76,22 +95,26 @@ class VierIE(InfoExtractor):
'pass': password,
}),
headers={'Content-Type': 'application/x-www-form-urlencoded'})
self.logged_in = True
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
embed_id = mobj.group('embed_id')
display_id = mobj.group('display_id') or embed_id
video_id = mobj.group('id') or embed_id
site = mobj.group('site')
if not self._logged_in:
self._login(site)
webpage = self._download_webpage(url, display_id)
if r'id="user-login"' in webpage:
self._login(site)
webpage = self._download_webpage(url, display_id)
self.report_warning('Log in to extract metadata', video_id=video_id)
webpage = self._download_webpage(
'http://www.%s.be/video/v3/embed/%s' % (site, video_id),
display_id)
video_id = self._search_regex(
[r'data-nid="(\d+)"', r'"nid"\s*:\s*"(\d+)"'],
webpage, 'video id')
application = self._search_regex(
[r'data-application="([^"]+)"', r'"application"\s*:\s*"([^"]+)"'],
webpage, 'application', default=site + '_vod')