_ Git - youtube-dl/blob - youtube_dl/extractor/abcnews.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import calendar
   5 import re
   6 import time
   7
   8 from .amp import AMPIE
   9 from .common import InfoExtractor
  10 from ..compat import compat_urlparse
  11
  12
  13 class AbcNewsVideoIE(AMPIE):
  14     IE_NAME = 'abcnews:video'
  15     _VALID_URL = r'''(?x)
  16                     https?://
  17                         abcnews\.go\.com/
  18                         (?:
  19                             [^/]+/video/(?P<display_id>[0-9a-z-]+)-|
  20                             video/embed\?.*?\bid=
  21                         )
  22                         (?P<id>\d+)
  23                     '''
  24
  25     _TESTS = [{
  26         'url': 'http://abcnews.go.com/ThisWeek/video/week-exclusive-irans-foreign-minister-zarif-20411932',
  27         'info_dict': {
  28             'id': '20411932',
  29             'ext': 'mp4',
  30             'display_id': 'week-exclusive-irans-foreign-minister-zarif',
  31             'title': '\'This Week\' Exclusive: Iran\'s Foreign Minister Zarif',
  32             'description': 'George Stephanopoulos goes one-on-one with Iranian Foreign Minister Dr. Javad Zarif.',
  33             'duration': 180,
  34             'thumbnail': r're:^https?://.*\.jpg$',
  35         },
  36         'params': {
  37             # m3u8 download
  38             'skip_download': True,
  39         },
  40     }, {
  41         'url': 'http://abcnews.go.com/video/embed?id=46979033',
  42         'only_matching': True,
  43     }, {
  44         'url': 'http://abcnews.go.com/2020/video/2020-husband-stands-teacher-jail-student-affairs-26119478',
  45         'only_matching': True,
  46     }]
  47
  48     def _real_extract(self, url):
  49         mobj = re.match(self._VALID_URL, url)
  50         display_id = mobj.group('display_id')
  51         video_id = mobj.group('id')
  52         info_dict = self._extract_feed_info(
  53             'http://abcnews.go.com/video/itemfeed?id=%s' % video_id)
  54         info_dict.update({
  55             'id': video_id,
  56             'display_id': display_id,
  57         })
  58         return info_dict
  59
  60
  61 class AbcNewsIE(InfoExtractor):
  62     IE_NAME = 'abcnews'
  63     _VALID_URL = r'https?://abcnews\.go\.com/(?:[^/]+/)+(?P<display_id>[0-9a-z-]+)/story\?id=(?P<id>\d+)'
  64
  65     _TESTS = [{
  66         'url': 'http://abcnews.go.com/Blotter/News/dramatic-video-rare-death-job-america/story?id=10498713#.UIhwosWHLjY',
  67         'info_dict': {
  68             'id': '10498713',
  69             'ext': 'flv',
  70             'display_id': 'dramatic-video-rare-death-job-america',
  71             'title': 'Occupational Hazards',
  72             'description': 'Nightline investigates the dangers that lurk at various jobs.',
  73             'thumbnail': r're:^https?://.*\.jpg$',
  74             'upload_date': '20100428',
  75             'timestamp': 1272412800,
  76         },
  77         'add_ie': ['AbcNewsVideo'],
  78     }, {
  79         'url': 'http://abcnews.go.com/Entertainment/justin-timberlake-performs-stop-feeling-eurovision-2016/story?id=39125818',
  80         'info_dict': {
  81             'id': '39125818',
  82             'ext': 'mp4',
  83             'display_id': 'justin-timberlake-performs-stop-feeling-eurovision-2016',
  84             'title': 'Justin Timberlake Drops Hints For Secret Single',
  85             'description': 'Lara Spencer reports the buzziest stories of the day in "GMA" Pop News.',
  86             'upload_date': '20160515',
  87             'timestamp': 1463329500,
  88         },
  89         'params': {
  90             # m3u8 download
  91             'skip_download': True,
  92             # The embedded YouTube video is blocked due to copyright issues
  93             'playlist_items': '1',
  94         },
  95         'add_ie': ['AbcNewsVideo'],
  96     }, {
  97         'url': 'http://abcnews.go.com/Technology/exclusive-apple-ceo-tim-cook-iphone-cracking-software/story?id=37173343',
  98         'only_matching': True,
  99     }]
 100
 101     def _real_extract(self, url):
 102         mobj = re.match(self._VALID_URL, url)
 103         display_id = mobj.group('display_id')
 104         video_id = mobj.group('id')
 105
 106         webpage = self._download_webpage(url, video_id)
 107         video_url = self._search_regex(
 108             r'window\.abcnvideo\.url\s*=\s*"([^"]+)"', webpage, 'video URL')
 109         full_video_url = compat_urlparse.urljoin(url, video_url)
 110
 111         youtube_url = self._html_search_regex(
 112             r'<iframe[^>]+src="(https://www\.youtube\.com/embed/[^"]+)"',
 113             webpage, 'YouTube URL', default=None)
 114
 115         timestamp = None
 116         date_str = self._html_search_regex(
 117             r'<span[^>]+class="timestamp">([^<]+)</span>',
 118             webpage, 'timestamp', fatal=False)
 119         if date_str:
 120             tz_offset = 0
 121             if date_str.endswith(' ET'):  # Eastern Time
 122                 tz_offset = -5
 123                 date_str = date_str[:-3]
 124             date_formats = ['%b. %d, %Y', '%b %d, %Y, %I:%M %p']
 125             for date_format in date_formats:
 126                 try:
 127                     timestamp = calendar.timegm(time.strptime(date_str.strip(), date_format))
 128                 except ValueError:
 129                     continue
 130             if timestamp is not None:
 131                 timestamp -= tz_offset * 3600
 132
 133         entry = {
 134             '_type': 'url_transparent',
 135             'ie_key': AbcNewsVideoIE.ie_key(),
 136             'url': full_video_url,
 137             'id': video_id,
 138             'display_id': display_id,
 139             'timestamp': timestamp,
 140         }
 141
 142         if youtube_url:
 143             entries = [entry, self.url_result(youtube_url, 'Youtube')]
 144             return self.playlist_result(entries)
 145
 146         return entry