2 from __future__ import unicode_literals
7 from .common import InfoExtractor
14 class WatIE(InfoExtractor):
15 _VALID_URL = r'http://www\.wat\.tv/video/(?P<display_id>.*)-(?P<short_id>.*?)_.*?\.html'
19 'url': 'http://www.wat.tv/video/soupe-figues-l-orange-aux-epices-6z1uz_2hvf7_.html',
20 'md5': 'ce70e9223945ed26a8056d413ca55dc9',
23 'display_id': 'soupe-figues-l-orange-aux-epices',
25 'title': 'Soupe de figues à l\'orange et aux épices',
26 'description': 'Retrouvez l\'émission "Petits plats en équilibre", diffusée le 18 août 2014.',
27 'upload_date': '20140819',
32 'url': 'http://www.wat.tv/video/gregory-lemarchal-voix-ange-6z1v7_6ygkj_.html',
33 'md5': 'fbc84e4378165278e743956d9c1bf16b',
36 'display_id': 'gregory-lemarchal-voix-ange',
38 'title': 'Grégory Lemarchal, une voix d\'ange depuis 10 ans (1/3)',
39 'description': 'md5:b7a849cf16a2b733d9cd10c52906dee3',
40 'upload_date': '20140816',
46 def download_video_info(self, real_id):
47 # 'contentv4' is used in the website, but it also returns the related
48 # videos, we don't need them
49 info = self._download_json('http://www.wat.tv/interface/contentv3/' + real_id, real_id)
52 def _real_extract(self, url):
53 def real_id_for_chapter(chapter):
54 return chapter['tc_start'].split('-')[0]
55 mobj = re.match(self._VALID_URL, url)
56 short_id = mobj.group('short_id')
57 display_id = mobj.group('display_id')
58 webpage = self._download_webpage(url, display_id or short_id)
59 real_id = self._search_regex(r'xtpage = ".*-(.*?)";', webpage, 'real id')
61 video_info = self.download_video_info(real_id)
63 error_desc = video_info.get('error_desc')
66 '%s returned error: %s' % (self.IE_NAME, error_desc), expected=True)
68 geo_list = video_info.get('geoList')
69 country = geo_list[0] if geo_list else ''
71 chapters = video_info['chapters']
72 first_chapter = chapters[0]
73 files = video_info['files']
76 if real_id_for_chapter(first_chapter) != real_id:
77 self.to_screen('Multipart video detected')
79 for chapter in chapters:
80 chapter_id = real_id_for_chapter(chapter)
81 # Yes, when we this chapter is processed by WatIE,
82 # it will download the info again
83 chapter_info = self.download_video_info(chapter_id)
84 chapter_urls.append(chapter_info['url'])
85 entries = [self.url_result(chapter_url) for chapter_url in chapter_urls]
86 return self.playlist_result(entries, real_id, video_info['title'])
89 if 'date_diffusion' in first_chapter:
90 upload_date = unified_strdate(first_chapter['date_diffusion'])
91 # Otherwise we can continue and extract just one part, we have to use
92 # the short id for getting the video url
95 'url': 'http://wat.tv/get/android5/%s.mp4' % real_id,
96 'format_id': 'Mobile',
99 fmts = [('SD', 'web')]
100 if first_file.get('hasHD'):
101 fmts.append(('HD', 'webhd'))
103 def compute_token(param):
104 timestamp = '%08x' % int(self._download_webpage(
105 'http://www.wat.tv/servertime', real_id,
106 'Downloading server time').split('|')[0])
107 magic = '9b673b13fa4682ed14c3cfa5af5310274b514c4133e9b3a81e6e3aba009l2564'
108 return '%s/%s' % (hashlib.md5((magic + param + timestamp).encode('ascii')).hexdigest(), timestamp)
111 webid = '/%s/%s' % (fmt[1], real_id)
112 video_url = self._download_webpage(
113 'http://www.wat.tv/get%s?token=%s&getURL=1&country=%s' % (webid, compute_token(webid), country),
115 'Downloding %s video URL' % fmt[0],
116 'Failed to download %s video URL' % fmt[0],
128 'display_id': display_id,
129 'title': first_chapter['title'],
130 'thumbnail': first_chapter['preview'],
131 'description': first_chapter['description'],
132 'view_count': video_info['views'],
133 'upload_date': upload_date,
134 'duration': first_file['duration'],