Merge branch 'master' of https://github.com/DarkstaIkers/youtube-dl into DarkstaIkers...
[youtube-dl] / youtube_dl / extractor / ellentv.py
1 # coding: utf-8
2 from __future__ import unicode_literals
3
4 import json
5
6 from .common import InfoExtractor
7 from ..utils import (
8     ExtractorError,
9     NO_DEFAULT,
10 )
11
12
13 class EllenTVIE(InfoExtractor):
14     _VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P<id>[a-z0-9_-]+)'
15     _TESTS = [{
16         'url': 'http://www.ellentv.com/videos/0-ipq1gsai/',
17         'md5': '4294cf98bc165f218aaa0b89e0fd8042',
18         'info_dict': {
19             'id': '0_ipq1gsai',
20             'ext': 'mov',
21             'title': 'Fast Fingers of Fate',
22             'description': 'md5:3539013ddcbfa64b2a6d1b38d910868a',
23             'timestamp': 1428035648,
24             'upload_date': '20150403',
25             'uploader_id': 'batchUser',
26         },
27     }, {
28         # not available via http://widgets.ellentube.com/
29         'url': 'http://www.ellentv.com/videos/1-szkgu2m2/',
30         'info_dict': {
31             'id': '1_szkgu2m2',
32             'ext': 'flv',
33             'title': "Ellen's Amazingly Talented Audience",
34             'description': 'md5:86ff1e376ff0d717d7171590e273f0a5',
35             'timestamp': 1255140900,
36             'upload_date': '20091010',
37             'uploader_id': 'ellenkaltura@gmail.com',
38         },
39         'params': {
40             'skip_download': True,
41         },
42     }]
43
44     def _real_extract(self, url):
45         video_id = self._match_id(url)
46
47         URLS = ('http://widgets.ellentube.com/videos/%s' % video_id, url)
48
49         for num, url_ in enumerate(URLS, 1):
50             webpage = self._download_webpage(
51                 url_, video_id, fatal=num == len(URLS))
52
53             default = NO_DEFAULT if num == len(URLS) else None
54
55             partner_id = self._search_regex(
56                 r"var\s+partnerId\s*=\s*'([^']+)", webpage, 'partner id',
57                 default=default)
58
59             kaltura_id = self._search_regex(
60                 [r'id="kaltura_player_([^"]+)"',
61                  r"_wb_entry_id\s*:\s*'([^']+)",
62                  r'data-kaltura-entry-id="([^"]+)'],
63                 webpage, 'kaltura id', default=default)
64
65             if partner_id and kaltura_id:
66                 break
67
68         return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura')
69
70
71 class EllenTVClipsIE(InfoExtractor):
72     IE_NAME = 'EllenTV:clips'
73     _VALID_URL = r'https?://(?:www\.)?ellentv\.com/episodes/(?P<id>[a-z0-9_-]+)'
74     _TEST = {
75         'url': 'http://www.ellentv.com/episodes/meryl-streep-vanessa-hudgens/',
76         'info_dict': {
77             'id': 'meryl-streep-vanessa-hudgens',
78             'title': 'Meryl Streep, Vanessa Hudgens',
79         },
80         'playlist_mincount': 7,
81     }
82
83     def _real_extract(self, url):
84         playlist_id = self._match_id(url)
85
86         webpage = self._download_webpage(url, playlist_id)
87         playlist = self._extract_playlist(webpage)
88
89         return {
90             '_type': 'playlist',
91             'id': playlist_id,
92             'title': self._og_search_title(webpage),
93             'entries': self._extract_entries(playlist)
94         }
95
96     def _extract_playlist(self, webpage):
97         json_string = self._search_regex(r'playerView.addClips\(\[\{(.*?)\}\]\);', webpage, 'json')
98         try:
99             return json.loads('[{' + json_string + '}]')
100         except ValueError as ve:
101             raise ExtractorError('Failed to download JSON', cause=ve)
102
103     def _extract_entries(self, playlist):
104         return [
105             self.url_result(
106                 'kaltura:%s:%s' % (item['kaltura_partner_id'], item['kaltura_entry_id']),
107                 'Kaltura')
108             for item in playlist]