youtube-dl/youtube_dl/extractor/ellentv.py

102 lines
3.5 KiB
Python
Raw Normal View History

2014-08-13 10:14:44 +00:00
# coding: utf-8
from __future__ import unicode_literals
2014-08-21 09:57:03 +00:00
from .common import InfoExtractor
2017-01-09 17:22:53 +00:00
from .kaltura import KalturaIE
from ..utils import NO_DEFAULT
2014-08-21 09:57:03 +00:00
2014-08-13 10:14:44 +00:00
class EllenTVIE(InfoExtractor):
2015-01-03 15:44:47 +00:00
_VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P<id>[a-z0-9_-]+)'
_TESTS = [{
2015-04-04 18:01:55 +00:00
'url': 'http://www.ellentv.com/videos/0-ipq1gsai/',
2015-12-11 22:40:12 +00:00
'md5': '4294cf98bc165f218aaa0b89e0fd8042',
2014-08-13 10:14:44 +00:00
'info_dict': {
2015-04-24 16:07:15 +00:00
'id': '0_ipq1gsai',
2015-12-11 22:40:12 +00:00
'ext': 'mov',
2015-04-04 18:01:55 +00:00
'title': 'Fast Fingers of Fate',
2015-12-11 22:40:12 +00:00
'description': 'md5:3539013ddcbfa64b2a6d1b38d910868a',
2015-04-24 16:07:15 +00:00
'timestamp': 1428035648,
2015-04-04 18:01:55 +00:00
'upload_date': '20150403',
2015-04-24 16:07:15 +00:00
'uploader_id': 'batchUser',
},
}, {
# not available via http://widgets.ellentube.com/
'url': 'http://www.ellentv.com/videos/1-szkgu2m2/',
'info_dict': {
'id': '1_szkgu2m2',
'ext': 'flv',
'title': "Ellen's Amazingly Talented Audience",
'description': 'md5:86ff1e376ff0d717d7171590e273f0a5',
'timestamp': 1255140900,
'upload_date': '20091010',
'uploader_id': 'ellenkaltura@gmail.com',
},
'params': {
'skip_download': True,
},
}]
2014-08-13 10:14:44 +00:00
def _real_extract(self, url):
2015-01-03 15:44:47 +00:00
video_id = self._match_id(url)
2014-08-13 10:14:44 +00:00
URLS = ('http://widgets.ellentube.com/videos/%s' % video_id, url)
for num, url_ in enumerate(URLS, 1):
webpage = self._download_webpage(
url_, video_id, fatal=num == len(URLS))
default = NO_DEFAULT if num == len(URLS) else None
partner_id = self._search_regex(
r"var\s+partnerId\s*=\s*'([^']+)", webpage, 'partner id',
default=default)
kaltura_id = self._search_regex(
[r'id="kaltura_player_([^"]+)"',
r"_wb_entry_id\s*:\s*'([^']+)",
r'data-kaltura-entry-id="([^"]+)'],
webpage, 'kaltura id', default=default)
2014-08-13 10:14:44 +00:00
if partner_id and kaltura_id:
break
2015-04-24 16:03:14 +00:00
2017-01-09 17:22:53 +00:00
return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id), KalturaIE.ie_key())
2014-08-13 10:14:44 +00:00
2014-08-21 09:57:03 +00:00
2014-08-13 10:14:44 +00:00
class EllenTVClipsIE(InfoExtractor):
2014-08-21 09:57:03 +00:00
IE_NAME = 'EllenTV:clips'
2014-08-13 10:14:44 +00:00
_VALID_URL = r'https?://(?:www\.)?ellentv\.com/episodes/(?P<id>[a-z0-9_-]+)'
_TEST = {
'url': 'http://www.ellentv.com/episodes/meryl-streep-vanessa-hudgens/',
'info_dict': {
2014-08-21 09:57:03 +00:00
'id': 'meryl-streep-vanessa-hudgens',
'title': 'Meryl Streep, Vanessa Hudgens',
},
2017-01-09 17:22:53 +00:00
'playlist_mincount': 5,
2014-08-13 10:14:44 +00:00
}
def _real_extract(self, url):
2015-01-03 15:44:47 +00:00
playlist_id = self._match_id(url)
2014-08-13 10:14:44 +00:00
webpage = self._download_webpage(url, playlist_id)
2017-01-09 17:22:53 +00:00
playlist = self._extract_playlist(webpage, playlist_id)
2014-08-13 10:14:44 +00:00
return {
'_type': 'playlist',
'id': playlist_id,
'title': self._og_search_title(webpage),
'entries': self._extract_entries(playlist)
}
2017-01-09 17:22:53 +00:00
def _extract_playlist(self, webpage, playlist_id):
2014-08-13 10:14:44 +00:00
json_string = self._search_regex(r'playerView.addClips\(\[\{(.*?)\}\]\);', webpage, 'json')
2017-01-09 17:22:53 +00:00
return self._parse_json('[{' + json_string + '}]', playlist_id)
2014-08-13 10:14:44 +00:00
def _extract_entries(self, playlist):
2015-04-24 16:09:54 +00:00
return [
self.url_result(
'kaltura:%s:%s' % (item['kaltura_partner_id'], item['kaltura_entry_id']),
2017-01-09 17:22:53 +00:00
KalturaIE.ie_key(), video_id=item['kaltura_entry_id'])
2015-04-24 16:09:54 +00:00
for item in playlist]