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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     js_to_json,
   7     mimetype2ext,
   8     determine_ext,
   9     update_url_query,
  10     get_element_by_attribute,
  11     int_or_none,
  12 )
  13
  14
  15 class NobelPrizeIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?nobelprize\.org/mediaplayer.*?\bid=(?P<id>\d+)'
  17     _TEST = {
  18         'url': 'http://www.nobelprize.org/mediaplayer/?id=2636',
  19         'md5': '04c81e5714bb36cc4e2232fee1d8157f',
  20         'info_dict': {
  21             'id': '2636',
  22             'ext': 'mp4',
  23             'title': 'Announcement of the 2016 Nobel Prize in Physics',
  24             'description': 'md5:05beba57f4f5a4bbd4cf2ef28fcff739',
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         video_id = self._match_id(url)
  30         webpage = self._download_webpage(url, video_id)
  31         media = self._parse_json(self._search_regex(
  32             r'(?s)var\s*config\s*=\s*({.+?});', webpage,
  33             'config'), video_id, js_to_json)['media']
  34         title = media['title']
  35
  36         formats = []
  37         for source in media.get('source', []):
  38             source_src = source.get('src')
  39             if not source_src:
  40                 continue
  41             ext = mimetype2ext(source.get('type')) or determine_ext(source_src)
  42             if ext == 'm3u8':
  43                 formats.extend(self._extract_m3u8_formats(
  44                     source_src, video_id, 'mp4', 'm3u8_native',
  45                     m3u8_id='hls', fatal=False))
  46             elif ext == 'f4m':
  47                 formats.extend(self._extract_f4m_formats(
  48                     update_url_query(source_src, {'hdcore': '3.7.0'}),
  49                     video_id, f4m_id='hds', fatal=False))
  50             else:
  51                 formats.append({
  52                     'url': source_src,
  53                 })
  54         self._sort_formats(formats)
  55
  56         return {
  57             'id': video_id,
  58             'title': title,
  59             'description': get_element_by_attribute('itemprop', 'description', webpage),
  60             'duration': int_or_none(media.get('duration')),
  61             'formats': formats,
  62         }