Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/tv2hu.py

   1 # encoding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import int_or_none
   6
   7
   8 class TV2HuIE(InfoExtractor):
   9     IE_NAME = 'tv2.hu'
  10     _VALID_URL = r'https?://(?:www\.)?tv2\.hu/(?:[^/]+/)+(?P<id>\d+)_[^/?#]+?\.html'
  11     _TESTS = [{
  12         'url': 'http://tv2.hu/ezek_megorultek/217679_ezek-megorultek---1.-adas-1.-resz.html',
  13         'md5': '585e58e2e090f34603804bb2c48e98d8',
  14         'info_dict': {
  15             'id': '217679',
  16             'ext': 'mp4',
  17             'title': 'Ezek megőrültek! - 1. adás 1. rész',
  18             'upload_date': '20160826',
  19             'thumbnail': r're:^https?://.*\.jpg$'
  20         }
  21     }, {
  22         'url': 'http://tv2.hu/ezek_megorultek/teljes_adasok/217677_ezek-megorultek---1.-adas-2.-resz.html',
  23         'only_matching': True
  24     }, {
  25         'url': 'http://tv2.hu/musoraink/aktiv/aktiv_teljes_adas/217963_aktiv-teljes-adas---2016.08.30..html',
  26         'only_matching': True
  27     }]
  28
  29     def _real_extract(self, url):
  30         video_id = self._match_id(url)
  31         webpage = self._download_webpage(url, video_id)
  32         json_url = self._search_regex(
  33             r'jsonUrl\s*=\s*"([^"]+)"', webpage, 'json url')
  34         json_data = self._download_json(json_url, video_id)
  35
  36         formats = []
  37         for b in ('bitrates', 'backupBitrates'):
  38             bitrates = json_data.get(b, {})
  39             m3u8_url = bitrates.get('hls')
  40             if m3u8_url:
  41                 formats.extend(self._extract_wowza_formats(
  42                     m3u8_url, video_id, skip_protocols=['rtmp', 'rtsp']))
  43
  44             for mp4_url in bitrates.get('mp4', []):
  45                 height = int_or_none(self._search_regex(
  46                     r'\.(\d+)p\.mp4', mp4_url, 'height', default=None))
  47                 formats.append({
  48                     'format_id': 'http' + ('-%d' % height if height else ''),
  49                     'url': mp4_url,
  50                     'height': height,
  51                     'width': int_or_none(height / 9.0 * 16.0 if height else None),
  52                 })
  53         self._sort_formats(formats)
  54
  55         return {
  56             'id': video_id,
  57             'title': self._og_search_title(webpage).strip(),
  58             'thumbnail': self._og_search_thumbnail(webpage),
  59             'upload_date': self._search_regex(
  60                 r'/vod/(\d{8})/', json_url, 'upload_date', default=None),
  61             'formats': formats,
  62         }