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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     smuggle_url,
   7     float_or_none,
   8     parse_iso8601,
   9     update_url_query,
  10 )
  11
  12
  13 class MovieClipsIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?movieclips\.com/videos/.+-(?P<id>\d+)(?:\?|$)'
  15     _TEST = {
  16         'url': 'http://www.movieclips.com/videos/warcraft-trailer-1-561180739597',
  17         'md5': '42b5a0352d4933a7bd54f2104f481244',
  18         'info_dict': {
  19             'id': 'pKIGmG83AqD9',
  20             'ext': 'mp4',
  21             'title': 'Warcraft Trailer 1',
  22             'description': 'Watch Trailer 1 from Warcraft (2016). Legendary’s WARCRAFT is a 3D epic adventure of world-colliding conflict based.',
  23             'thumbnail': r're:^https?://.*\.jpg$',
  24             'timestamp': 1446843055,
  25             'upload_date': '20151106',
  26             'uploader': 'Movieclips',
  27         },
  28         'add_ie': ['ThePlatform'],
  29     }
  30
  31     def _real_extract(self, url):
  32         video_id = self._match_id(url)
  33         webpage = self._download_webpage(url, video_id)
  34         video = next(v for v in self._parse_json(self._search_regex(
  35             r'var\s+__REACT_ENGINE__\s*=\s*({.+});',
  36             webpage, 'react engine'), video_id)['playlist']['videos'] if v['id'] == video_id)
  37
  38         return {
  39             '_type': 'url_transparent',
  40             'ie_key': 'ThePlatform',
  41             'url': smuggle_url(update_url_query(
  42                 video['contentUrl'], {'mbr': 'true'}), {'force_smil_url': True}),
  43             'title': self._og_search_title(webpage),
  44             'description': self._html_search_meta('description', webpage),
  45             'duration': float_or_none(video.get('duration')),
  46             'timestamp': parse_iso8601(video.get('dateCreated')),
  47             'thumbnail': video.get('defaultImage'),
  48             'uploader': video.get('provider'),
  49         }