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     float_or_none,
   9     ISO639Utils,
  10 )
  11
  12
  13 class AdobeTVIE(InfoExtractor):
  14     _VALID_URL = r'https?://tv\.adobe\.com/watch/[^/]+/(?P<id>[^/]+)'
  15
  16     _TEST = {
  17         'url': 'http://tv.adobe.com/watch/the-complete-picture-with-julieanne-kost/quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop/',
  18         'md5': '9bc5727bcdd55251f35ad311ca74fa1e',
  19         'info_dict': {
  20             'id': 'quick-tip-how-to-draw-a-circle-around-an-object-in-photoshop',
  21             'ext': 'mp4',
  22             'title': 'Quick Tip - How to Draw a Circle Around an Object in Photoshop',
  23             'description': 'md5:99ec318dc909d7ba2a1f2b038f7d2311',
  24             'thumbnail': 're:https?://.*\.jpg$',
  25             'upload_date': '20110914',
  26             'duration': 60,
  27             'view_count': int,
  28         },
  29     }
  30
  31     def _real_extract(self, url):
  32         video_id = self._match_id(url)
  33         webpage = self._download_webpage(url, video_id)
  34
  35         player = self._parse_json(
  36             self._search_regex(r'html5player:\s*({.+?})\s*\n', webpage, 'player'),
  37             video_id)
  38
  39         title = player.get('title') or self._search_regex(
  40             r'data-title="([^"]+)"', webpage, 'title')
  41         description = self._og_search_description(webpage)
  42         thumbnail = self._og_search_thumbnail(webpage)
  43
  44         upload_date = unified_strdate(
  45             self._html_search_meta('datepublished', webpage, 'upload date'))
  46
  47         duration = parse_duration(
  48             self._html_search_meta('duration', webpage, 'duration') or
  49             self._search_regex(
  50                 r'Runtime:\s*(\d{2}:\d{2}:\d{2})',
  51                 webpage, 'duration', fatal=False))
  52
  53         view_count = str_to_int(self._search_regex(
  54             r'<div class="views">\s*Views?:\s*([\d,.]+)\s*</div>',
  55             webpage, 'view count'))
  56
  57         formats = [{
  58             'url': source['src'],
  59             'format_id': source.get('quality') or source['src'].split('-')[-1].split('.')[0] or None,
  60             'tbr': source.get('bitrate'),
  61         } for source in player['sources']]
  62         self._sort_formats(formats)
  63
  64         return {
  65             'id': video_id,
  66             'title': title,
  67             'description': description,
  68             'thumbnail': thumbnail,
  69             'upload_date': upload_date,
  70             'duration': duration,
  71             'view_count': view_count,
  72             'formats': formats,
  73         }
  74
  75
  76 class AdobeTVVideoIE(InfoExtractor):
  77     _VALID_URL = r'https?://video\.tv\.adobe\.com/v/(?P<id>\d+)'
  78
  79     _TEST = {
  80         # From https://helpx.adobe.com/acrobat/how-to/new-experience-acrobat-dc.html?set=acrobat--get-started--essential-beginners
  81         'url': 'https://video.tv.adobe.com/v/2456/',
  82         'md5': '43662b577c018ad707a63766462b1e87',
  83         'info_dict': {
  84             'id': '2456',
  85             'ext': 'mp4',
  86             'title': 'New experience with Acrobat DC',
  87             'description': 'New experience with Acrobat DC',
  88             'duration': 248.667,
  89         },
  90     }
  91
  92     def _real_extract(self, url):
  93         video_id = self._match_id(url)
  94
  95         webpage = self._download_webpage(url, video_id)
  96
  97         player_params = self._parse_json(self._search_regex(
  98             r'var\s+bridge\s*=\s*([^;]+);', webpage, 'player parameters'),
  99             video_id)
 100
 101         formats = [{
 102             'url': source['src'],
 103             'width': source.get('width'),
 104             'height': source.get('height'),
 105             'tbr': source.get('bitrate'),
 106         } for source in player_params['sources']]
 107
 108         # For both metadata and downloaded files the duration varies among
 109         # formats. I just pick the max one
 110         duration = max(filter(None, [
 111             float_or_none(source.get('duration'), scale=1000)
 112             for source in player_params['sources']]))
 113
 114         subtitles = {}
 115         for translation in player_params.get('translations', []):
 116             lang_id = translation.get('language_w3c') or ISO639Utils.long2short(translation['language_medium'])
 117             if lang_id not in subtitles:
 118                 subtitles[lang_id] = []
 119             subtitles[lang_id].append({
 120                 'url': translation['vttPath'],
 121                 'ext': 'vtt',
 122             })
 123
 124         return {
 125             'id': video_id,
 126             'formats': formats,
 127             'title': player_params['title'],
 128             'description': self._og_search_description(webpage),
 129             'duration': duration,
 130             'subtitles': subtitles,
 131         }