]>
jfr.im git - yt-dlp.git/blob - youtube_dl/extractor/abcnews.py
2 from __future__
import unicode_literals
9 from .common
import InfoExtractor
10 from ..compat
import compat_urlparse
13 class AbcNewsVideoIE(AMPIE
):
14 IE_NAME
= 'abcnews:video'
15 _VALID_URL
= 'http://abcnews.go.com/[^/]+/video/(?P<display_id>[0-9a-z-]+)-(?P<id>\d+)'
18 'url': 'http://abcnews.go.com/ThisWeek/video/week-exclusive-irans-foreign-minister-zarif-20411932',
22 'display_id': 'week-exclusive-irans-foreign-minister-zarif',
23 'title': '\'This Week\' Exclusive: Iran\'s Foreign Minister Zarif',
24 'description': 'George Stephanopoulos goes one-on-one with Iranian Foreign Minister Dr. Javad Zarif.',
26 'thumbnail': 're:^https?://.*\.jpg$',
30 'skip_download': True,
33 'url': 'http://abcnews.go.com/2020/video/2020-husband-stands-teacher-jail-student-affairs-26119478',
34 'only_matching': True,
37 def _real_extract(self
, url
):
38 mobj
= re
.match(self
._VALID
_URL
, url
)
39 display_id
= mobj
.group('display_id')
40 video_id
= mobj
.group('id')
41 info_dict
= self
._extract
_feed
_info
(
42 'http://abcnews.go.com/video/itemfeed?id=%s' % video_id
)
45 'display_id': display_id
,
50 class AbcNewsIE(InfoExtractor
):
52 _VALID_URL
= 'https?://abcnews\.go\.com/(?:[^/]+/)+(?P<display_id>[0-9a-z-]+)/story\?id=(?P<id>\d+)'
55 'url': 'http://abcnews.go.com/Blotter/News/dramatic-video-rare-death-job-america/story?id=10498713#.UIhwosWHLjY',
59 'display_id': 'dramatic-video-rare-death-job-america',
60 'title': 'Occupational Hazards',
61 'description': 'Nightline investigates the dangers that lurk at various jobs.',
62 'thumbnail': 're:^https?://.*\.jpg$',
63 'upload_date': '20100428',
64 'timestamp': 1272412800,
66 'add_ie': ['AbcNewsVideo'],
68 'url': 'http://abcnews.go.com/Entertainment/justin-timberlake-performs-stop-feeling-eurovision-2016/story?id=39125818',
72 'display_id': 'justin-timberlake-performs-stop-feeling-eurovision-2016',
73 'title': 'Justin Timberlake Drops Hints For Secret Single',
74 'description': 'Lara Spencer reports the buzziest stories of the day in "GMA" Pop News.',
75 'upload_date': '20160515',
76 'timestamp': 1463329500,
80 'skip_download': True,
81 # The embedded YouTube video is blocked due to copyright issues
82 'playlist_items': '1',
84 'add_ie': ['AbcNewsVideo'],
86 'url': 'http://abcnews.go.com/Technology/exclusive-apple-ceo-tim-cook-iphone-cracking-software/story?id=37173343',
87 'only_matching': True,
90 def _real_extract(self
, url
):
91 mobj
= re
.match(self
._VALID
_URL
, url
)
92 display_id
= mobj
.group('display_id')
93 video_id
= mobj
.group('id')
95 webpage
= self
._download
_webpage
(url
, video_id
)
96 video_url
= self
._search
_regex
(
97 r
'window\.abcnvideo\.url\s*=\s*"([^"]+)"', webpage
, 'video URL')
98 full_video_url
= compat_urlparse
.urljoin(url
, video_url
)
100 youtube_url
= self
._html
_search
_regex
(
101 r
'<iframe[^>]+src="(https://www\.youtube\.com/embed/[^"]+)"',
102 webpage
, 'YouTube URL', default
=None)
105 date_str
= self
._html
_search
_regex
(
106 r
'<span[^>]+class="timestamp">([^<]+)</span>',
107 webpage
, 'timestamp', fatal
=False)
110 if date_str
.endswith(' ET'): # Eastern Time
112 date_str
= date_str
[:-3]
113 date_formats
= ['%b. %d, %Y', '%b %d, %Y, %I:%M %p']
114 for date_format
in date_formats
:
116 timestamp
= calendar
.timegm(time
.strptime(date_str
.strip(), date_format
))
119 if timestamp
is not None:
120 timestamp
-= tz_offset
* 3600
123 '_type': 'url_transparent',
124 'ie_key': AbcNewsVideoIE
.ie_key(),
125 'url': full_video_url
,
127 'display_id': display_id
,
128 'timestamp': timestamp
,
132 entries
= [entry
, self
.url_result(youtube_url
, 'Youtube')]
133 return self
.playlist_result(entries
)