_ Git - youtube-dl/blob - youtube_dl/extractor/mediaset.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from ..compat import compat_str
   8 from ..utils import (
   9     determine_ext,
  10     parse_duration,
  11     try_get,
  12     unified_strdate,
  13 )
  14
  15
  16 class MediasetIE(InfoExtractor):
  17     _VALID_URL = r'''(?x)
  18                     (?:
  19                         mediaset:|
  20                         https?://
  21                             (?:www\.)?video\.mediaset\.it/
  22                             (?:
  23                                 (?:video|on-demand)/(?:[^/]+/)+[^/]+_|
  24                                 player/playerIFrame(?:Twitter)?\.shtml\?.*?\bid=
  25                             )
  26                     )(?P<id>[0-9]+)
  27                     '''
  28     _TESTS = [{
  29         # full episode
  30         'url': 'http://www.video.mediaset.it/video/hello_goodbye/full/quarta-puntata_661824.html',
  31         'md5': '9b75534d42c44ecef7bf1ffeacb7f85d',
  32         'info_dict': {
  33             'id': '661824',
  34             'ext': 'mp4',
  35             'title': 'Quarta puntata',
  36             'description': 'md5:7183696d6df570e3412a5ef74b27c5e2',
  37             'thumbnail': r're:^https?://.*\.jpg$',
  38             'duration': 1414,
  39             'creator': 'mediaset',
  40             'upload_date': '20161107',
  41             'series': 'Hello Goodbye',
  42             'categories': ['reality'],
  43         },
  44         'expected_warnings': ['is not a supported codec'],
  45     }, {
  46         'url': 'http://www.video.mediaset.it/video/matrix/full_chiambretti/puntata-del-25-maggio_846685.html',
  47         'md5': '1276f966ac423d16ba255ce867de073e',
  48         'info_dict': {
  49             'id': '846685',
  50             'ext': 'mp4',
  51             'title': 'Puntata del 25 maggio',
  52             'description': 'md5:ee2e456e3eb1dba5e814596655bb5296',
  53             'thumbnail': r're:^https?://.*\.jpg$',
  54             'duration': 6565,
  55             'creator': 'mediaset',
  56             'upload_date': '20180525',
  57             'series': 'Matrix',
  58             'categories': ['infotainment'],
  59         },
  60         'expected_warnings': ['HTTP Error 403: Forbidden'],
  61     }, {
  62         # clip
  63         'url': 'http://www.video.mediaset.it/video/gogglebox/clip/un-grande-classico-della-commedia-sexy_661680.html',
  64         'only_matching': True,
  65     }, {
  66         # iframe simple
  67         'url': 'http://www.video.mediaset.it/player/playerIFrame.shtml?id=665924&autoplay=true',
  68         'only_matching': True,
  69     }, {
  70         # iframe twitter (from http://www.wittytv.it/se-prima-mi-fidavo-zero/)
  71         'url': 'https://www.video.mediaset.it/player/playerIFrameTwitter.shtml?id=665104&playrelated=false&autoplay=false&related=true&hidesocial=true',
  72         'only_matching': True,
  73     }, {
  74         'url': 'mediaset:661824',
  75         'only_matching': True,
  76     }]
  77
  78     @staticmethod
  79     def _extract_urls(webpage):
  80         return [
  81             mobj.group('url')
  82             for mobj in re.finditer(
  83                 r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>https?://(?:www\.)?video\.mediaset\.it/player/playerIFrame(?:Twitter)?\.shtml\?.*?\bid=\d+.*?)\1',
  84                 webpage)]
  85
  86     def _real_extract(self, url):
  87         video_id = self._match_id(url)
  88
  89         video = self._download_json(
  90             'https://www.video.mediaset.it/html/metainfo.sjson',
  91             video_id, 'Downloading media info', query={
  92                 'id': video_id
  93             })['video']
  94
  95         title = video['title']
  96         media_id = video.get('guid') or video_id
  97
  98         video_list = self._download_json(
  99             'http://cdnsel01.mediaset.net/GetCdn2018.aspx',
 100             video_id, 'Downloading video CDN JSON', query={
 101                 'streamid': media_id,
 102                 'format': 'json',
 103             })['videoList']
 104
 105         formats = []
 106         for format_url in video_list:
 107             ext = determine_ext(format_url)
 108             if ext == 'm3u8':
 109                 formats.extend(self._extract_m3u8_formats(
 110                     format_url, video_id, 'mp4', entry_protocol='m3u8_native',
 111                     m3u8_id='hls', fatal=False))
 112             elif ext == 'mpd':
 113                 formats.extend(self._extract_mpd_formats(
 114                     format_url, video_id, mpd_id='dash', fatal=False))
 115             elif ext == 'ism' or '.ism' in format_url:
 116                 formats.extend(self._extract_ism_formats(
 117                     format_url, video_id, ism_id='mss', fatal=False))
 118             else:
 119                 formats.append({
 120                     'url': format_url,
 121                     'format_id': determine_ext(format_url),
 122                 })
 123         self._sort_formats(formats)
 124
 125         creator = try_get(
 126             video, lambda x: x['brand-info']['publisher'], compat_str)
 127         category = try_get(
 128             video, lambda x: x['brand-info']['category'], compat_str)
 129         categories = [category] if category else None
 130
 131         return {
 132             'id': video_id,
 133             'title': title,
 134             'description': video.get('short-description'),
 135             'thumbnail': video.get('thumbnail'),
 136             'duration': parse_duration(video.get('duration')),
 137             'creator': creator,
 138             'upload_date': unified_strdate(video.get('production-date')),
 139             'webpage_url': video.get('url'),
 140             'series': video.get('brand-value'),
 141             'season': video.get('season'),
 142             'categories': categories,
 143             'formats': formats,
 144         }