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

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     parse_duration,
   6     unified_strdate,
   7     str_to_int,
   8 )
   9
  10
  11 class AdobeTVIE(InfoExtractor):
  12     _VALID_URL = r'https?://tv\.adobe\.com/watch/[^/]+/(?P<id>[^/]+)'
  13
  14     _TEST = {
  15         'url': 'http://tv.adobe.com/watch/the-complete-picture-with-julieanne-kost/quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop/',
  16         'md5': '9bc5727bcdd55251f35ad311ca74fa1e',
  17         'info_dict': {
  18             'id': 'quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop',
  19             'ext': 'mp4',
  20             'title': 'Quick Tip - How to Draw a Circle Around an Object in Photoshop',
  21             'description': 'md5:99ec318dc909d7ba2a1f2b038f7d2311',
  22             'thumbnail': 're:https?://.*\.jpg$',
  23             'upload_date': '20110914',
  24             'duration': 60,
  25             'view_count': int,
  26         },
  27     }
  28
  29     def _real_extract(self, url):
  30         video_id = self._match_id(url)
  31
  32         webpage = self._download_webpage(url, video_id)
  33
  34         player = self._parse_json(
  35             self._search_regex(r'html5player:\s*({.+?})\s*\n', webpage, 'player'),
  36             video_id)
  37
  38         title = player.get('title') or self._search_regex(
  39             r'data-title="([^"]+)"', webpage, 'title')
  40         description = self._og_search_description(webpage)
  41         thumbnail = self._og_search_thumbnail(webpage)
  42
  43         upload_date = unified_strdate(
  44             self._html_search_meta('datepublished', webpage, 'upload date'))
  45
  46         duration = parse_duration(
  47             self._html_search_meta('duration', webpage, 'duration')
  48             or self._search_regex(r'Runtime:\s*(\d{2}:\d{2}:\d{2})', webpage, 'duration'))
  49
  50         view_count = str_to_int(self._search_regex(
  51             r'<div class="views">\s*Views?:\s*([\d,.]+)\s*</div>',
  52             webpage, 'view count'))
  53
  54         formats = [{
  55             'url': source['src'],
  56             'format_id': source.get('quality') or source['src'].split('-')[-1].split('.')[0] or None,
  57             'tbr': source.get('bitrate'),
  58         } for source in player['sources']]
  59         self._sort_formats(formats)
  60
  61         return {
  62             'id': video_id,
  63             'title': title,
  64             'description': description,
  65             'thumbnail': thumbnail,
  66             'upload_date': upload_date,
  67             'duration': duration,
  68             'view_count': view_count,
  69             'formats': formats,
  70         }