Raphaël G. Git Repositories - youtubedl/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         # clip
  47         'url': 'http://www.video.mediaset.it/video/gogglebox/clip/un-grande-classico-della-commedia-sexy_661680.html',
  48         'only_matching': True,
  49     }, {
  50         # iframe simple
  51         'url': 'http://www.video.mediaset.it/player/playerIFrame.shtml?id=665924&autoplay=true',
  52         'only_matching': True,
  53     }, {
  54         # iframe twitter (from http://www.wittytv.it/se-prima-mi-fidavo-zero/)
  55         'url': 'https://www.video.mediaset.it/player/playerIFrameTwitter.shtml?id=665104&playrelated=false&autoplay=false&related=true&hidesocial=true',
  56         'only_matching': True,
  57     }, {
  58         'url': 'mediaset:661824',
  59         'only_matching': True,
  60     }]
  61
  62     @staticmethod
  63     def _extract_urls(webpage):
  64         return [
  65             mobj.group('url')
  66             for mobj in re.finditer(
  67                 r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>https?://(?:www\.)?video\.mediaset\.it/player/playerIFrame(?:Twitter)?\.shtml\?.*?\bid=\d+.*?)\1',
  68                 webpage)]
  69
  70     def _real_extract(self, url):
  71         video_id = self._match_id(url)
  72
  73         video_list = self._download_json(
  74             'http://cdnsel01.mediaset.net/GetCdn.aspx',
  75             video_id, 'Downloading video CDN JSON', query={
  76                 'streamid': video_id,
  77                 'format': 'json',
  78             })['videoList']
  79
  80         formats = []
  81         for format_url in video_list:
  82             if '.ism' in format_url:
  83                 formats.extend(self._extract_ism_formats(
  84                     format_url, video_id, ism_id='mss', fatal=False))
  85             else:
  86                 formats.append({
  87                     'url': format_url,
  88                     'format_id': determine_ext(format_url),
  89                 })
  90         self._sort_formats(formats)
  91
  92         mediainfo = self._download_json(
  93             'http://plr.video.mediaset.it/html/metainfo.sjson',
  94             video_id, 'Downloading video info JSON', query={
  95                 'id': video_id,
  96             })['video']
  97
  98         title = mediainfo['title']
  99
 100         creator = try_get(
 101             mediainfo, lambda x: x['brand-info']['publisher'], compat_str)
 102         category = try_get(
 103             mediainfo, lambda x: x['brand-info']['category'], compat_str)
 104         categories = [category] if category else None
 105
 106         return {
 107             'id': video_id,
 108             'title': title,
 109             'description': mediainfo.get('short-description'),
 110             'thumbnail': mediainfo.get('thumbnail'),
 111             'duration': parse_duration(mediainfo.get('duration')),
 112             'creator': creator,
 113             'upload_date': unified_strdate(mediainfo.get('production-date')),
 114             'webpage_url': mediainfo.get('url'),
 115             'series': mediainfo.get('brand-value'),
 116             'categories': categories,
 117             'formats': formats,
 118         }