Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/aenetworks.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     smuggle_url,
   8     update_url_query,
   9     unescapeHTML,
  10 )
  11
  12
  13 class AENetworksIE(InfoExtractor):
  14     IE_NAME = 'aenetworks'
  15     IE_DESC = 'A+E Networks: A&E, Lifetime, History.com, FYI Network'
  16     _VALID_URL = r'https?://(?:www\.)?(?:(?:history|aetv|mylifetime)\.com|fyi\.tv)/(?P<type>[^/]+)/(?:[^/]+/)+(?P<id>[^/]+?)(?:$|[?#])'
  17
  18     _TESTS = [{
  19         'url': 'http://www.history.com/topics/valentines-day/history-of-valentines-day/videos/bet-you-didnt-know-valentines-day?m=528e394da93ae&s=undefined&f=1&free=false',
  20         'info_dict': {
  21             'id': 'g12m5Gyt3fdR',
  22             'ext': 'mp4',
  23             'title': "Bet You Didn't Know: Valentine's Day",
  24             'description': 'md5:7b57ea4829b391995b405fa60bd7b5f7',
  25             'timestamp': 1375819729,
  26             'upload_date': '20130806',
  27             'uploader': 'AENE-NEW',
  28         },
  29         'params': {
  30             # m3u8 download
  31             'skip_download': True,
  32         },
  33         'add_ie': ['ThePlatform'],
  34         'expected_warnings': ['JSON-LD'],
  35     }, {
  36         'url': 'http://www.history.com/shows/mountain-men/season-1/episode-1',
  37         'md5': '8ff93eb073449f151d6b90c0ae1ef0c7',
  38         'info_dict': {
  39             'id': 'eg47EERs_JsZ',
  40             'ext': 'mp4',
  41             'title': 'Winter Is Coming',
  42             'description': 'md5:641f424b7a19d8e24f26dea22cf59d74',
  43             'timestamp': 1338306241,
  44             'upload_date': '20120529',
  45             'uploader': 'AENE-NEW',
  46         },
  47         'add_ie': ['ThePlatform'],
  48     }, {
  49         'url': 'http://www.aetv.com/shows/duck-dynasty/video/inlawful-entry',
  50         'only_matching': True
  51     }, {
  52         'url': 'http://www.fyi.tv/shows/tiny-house-nation/videos/207-sq-ft-minnesota-prairie-cottage',
  53         'only_matching': True
  54     }, {
  55         'url': 'http://www.mylifetime.com/shows/project-runway-junior/video/season-1/episode-6/superstar-clients',
  56         'only_matching': True
  57     }]
  58
  59     def _real_extract(self, url):
  60         page_type, video_id = re.match(self._VALID_URL, url).groups()
  61
  62         webpage = self._download_webpage(url, video_id)
  63
  64         video_url_re = [
  65             r'data-href="[^"]*/%s"[^>]+data-release-url="([^"]+)"' % video_id,
  66             r"media_url\s*=\s*'([^']+)'"
  67         ]
  68         video_url = unescapeHTML(self._search_regex(video_url_re, webpage, 'video url'))
  69         query = {'mbr': 'true'}
  70         if page_type == 'shows':
  71             query['assetTypes'] = 'medium_video_s3'
  72         if 'switch=hds' in video_url:
  73             query['switch'] = 'hls'
  74
  75         info = self._search_json_ld(webpage, video_id, fatal=False)
  76         info.update({
  77             '_type': 'url_transparent',
  78             'url': smuggle_url(
  79                 update_url_query(video_url, query),
  80                 {
  81                     'sig': {
  82                         'key': 'crazyjava',
  83                         'secret': 's3cr3t'},
  84                     'force_smil_url': True
  85                 }),
  86         })
  87         return info