yt_dlp/extractor/wat.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..compat import compat_str
   6 from ..utils import (
   7     ExtractorError,
   8     int_or_none,
   9     try_get,
  10     unified_strdate,
  11 )
  12
  13
  14 class WatIE(InfoExtractor):
  15     _VALID_URL = r'(?:wat:|https?://(?:www\.)?wat\.tv/video/.*-)(?P<id>[0-9a-z]+)'
  16     IE_NAME = 'wat.tv'
  17     _TESTS = [
  18         {
  19             'url': 'http://www.wat.tv/video/soupe-figues-l-orange-aux-epices-6z1uz_2hvf7_.html',
  20             'info_dict': {
  21                 'id': '11713067',
  22                 'ext': 'mp4',
  23                 'title': 'Soupe de figues à l\'orange et aux épices',
  24                 'description': 'Retrouvez l\'émission "Petits plats en équilibre", diffusée le 18 août 2014.',
  25                 'upload_date': '20140819',
  26                 'duration': 120,
  27             },
  28             'params': {
  29                 # m3u8 download
  30                 'skip_download': True,
  31             },
  32             'expected_warnings': ['HTTP Error 404'],
  33             'skip': 'This content is no longer available',
  34         },
  35         {
  36             'url': 'http://www.wat.tv/video/gregory-lemarchal-voix-ange-6z1v7_6ygkj_.html',
  37             'md5': 'b16574df2c3cd1a36ca0098f2a791925',
  38             'info_dict': {
  39                 'id': '11713075',
  40                 'ext': 'mp4',
  41                 'title': 'Grégory Lemarchal, une voix d\'ange depuis 10 ans (1/3)',
  42                 'upload_date': '20140816',
  43             },
  44             'expected_warnings': ["Ce contenu n'est pas disponible pour l'instant."],
  45             'skip': 'This content is no longer available',
  46         },
  47     ]
  48     _GEO_BYPASS = False
  49
  50     def _real_extract(self, url):
  51         video_id = self._match_id(url)
  52         video_id = video_id if video_id.isdigit() and len(video_id) > 6 else compat_str(int(video_id, 36))
  53
  54         # 'contentv4' is used in the website, but it also returns the related
  55         # videos, we don't need them
  56         # video_data = self._download_json(
  57         #     'http://www.wat.tv/interface/contentv4s/' + video_id, video_id)
  58         video_data = self._download_json(
  59             'https://mediainfo.tf1.fr/mediainfocombo/' + video_id,
  60             video_id, query={'context': 'MYTF1'})
  61         video_info = video_data['media']
  62
  63         error_desc = video_info.get('error_desc')
  64         if error_desc:
  65             if video_info.get('error_code') == 'GEOBLOCKED':
  66                 self.raise_geo_restricted(error_desc, video_info.get('geoList'))
  67             raise ExtractorError(error_desc, expected=True)
  68
  69         title = video_info['title']
  70
  71         formats = []
  72         subtitles = {}
  73
  74         def extract_formats(manifest_urls):
  75             for f, f_url in manifest_urls.items():
  76                 if not f_url:
  77                     continue
  78                 if f in ('dash', 'mpd'):
  79                     fmts, subs = self._extract_mpd_formats_and_subtitles(
  80                         f_url.replace('://das-q1.tf1.fr/', '://das-q1-ssl.tf1.fr/'),
  81                         video_id, mpd_id='dash', fatal=False)
  82                 elif f == 'hls':
  83                     fmts, subs = self._extract_m3u8_formats_and_subtitles(
  84                         f_url, video_id, 'mp4',
  85                         'm3u8_native', m3u8_id='hls', fatal=False)
  86                 else:
  87                     continue
  88                 formats.extend(fmts)
  89                 self._merge_subtitles(subs, target=subtitles)
  90
  91         delivery = video_data.get('delivery') or {}
  92         extract_formats({delivery.get('format'): delivery.get('url')})
  93         if not formats:
  94             if delivery.get('drm'):
  95                 self.report_drm(video_id)
  96             manifest_urls = self._download_json(
  97                 'http://www.wat.tv/get/webhtml/' + video_id, video_id, fatal=False)
  98             if manifest_urls:
  99                 extract_formats(manifest_urls)
 100
 101         self._sort_formats(formats)
 102
 103         return {
 104             'id': video_id,
 105             'title': title,
 106             'thumbnail': video_info.get('preview'),
 107             'upload_date': unified_strdate(try_get(
 108                 video_data, lambda x: x['mediametrie']['chapters'][0]['estatS4'])),
 109             'duration': int_or_none(video_info.get('duration')),
 110             'formats': formats,
 111             'subtitles': subtitles,
 112         }