mollusk/youtube-dl
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

[amp] Add generic extractor for Akamai AMP feeds and use it in dramafever and foxnews extractors

Browse Source
This commit is contained in:
remitamine
2015-11-07 16:54:35 +01:00
parent 5d0f84d32c
commit 3793090b1b
3 changed files with 105 additions and 108 deletions
Download Patch File Download Diff File Expand all files Collapse all files

64
youtube_dl/extractor/foxnews.py
View File

@ -2,14 +2,14 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .amp import AMPIE
from ..utils import (
parse_iso8601,
int_or_none,
)
class FoxNewsIE(InfoExtractor):
class FoxNewsIE(AMPIE):
IE_DESC = 'Fox News and Fox Business Video'
_VALID_URL = r'https?://(?P<host>video\.fox(?:news|business)\.com)/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)'
_TESTS = [
@ -20,10 +20,10 @@ class FoxNewsIE(InfoExtractor):
'id': '3937480',
'ext': 'flv',
'title': 'Frozen in Time',
'description': 'Doctors baffled by 16-year-old girl that is the size of a toddler',
'description': '16-year-old girl is size of toddler',
'duration': 265,
'timestamp': 1304411491,
'upload_date': '20110503',
#'timestamp': 1304411491,
#'upload_date': '20110503',
'thumbnail': 're:^https?://.*\.jpg$',
},
},
@ -34,10 +34,10 @@ class FoxNewsIE(InfoExtractor):
'id': '3922535568001',
'ext': 'mp4',
'title': "Rep. Luis Gutierrez on if Obama's immigration plan is legal",
'description': "Congressman discusses the president's executive action",
'description': "Congressman discusses president's plan",
'duration': 292,
'timestamp': 1417662047,
'upload_date': '20141204',
#'timestamp': 1417662047,
#'upload_date': '20141204',
'thumbnail': 're:^https?://.*\.jpg$',
},
},
@ -56,48 +56,6 @@ class FoxNewsIE(InfoExtractor):
video_id = mobj.group('id')
host = mobj.group('host')
video = self._download_json(
'http://%s/v/feed/video/%s.js?template=fox' % (host, video_id), video_id)
item = video['channel']['item']
title = item['title']
description = item['description']
timestamp = parse_iso8601(item['dc-date'])
media_group = item['media-group']
duration = None
formats = []
for media in media_group['media-content']:
attributes = media['@attributes']
video_url = attributes['url']
if video_url.endswith('.f4m'):
formats.extend(self._extract_f4m_formats(video_url + '?hdcore=3.4.0&plugin=aasp-3.4.0.132.124', video_id))
elif video_url.endswith('.m3u8'):
formats.extend(self._extract_m3u8_formats(video_url, video_id, 'flv'))
elif not video_url.endswith('.smil'):
duration = int_or_none(attributes.get('duration'))
formats.append({
'url': video_url,
'format_id': media['media-category']['@attributes']['label'],
'preference': 1,
'vbr': int_or_none(attributes.get('bitrate')),
'filesize': int_or_none(attributes.get('fileSize'))
})
self._sort_formats(formats)
media_thumbnail = media_group['media-thumbnail']['@attributes']
thumbnails = [{
'url': media_thumbnail['url'],
'width': int_or_none(media_thumbnail.get('width')),
'height': int_or_none(media_thumbnail.get('height')),
}] if media_thumbnail else []
return {
'id': video_id,
'title': title,
'description': description,
'duration': duration,
'timestamp': timestamp,
'formats': formats,
'thumbnails': thumbnails,
}
info = self._extract_feed_info('http://%s/v/feed/video/%s.js?template=fox' % (host, video_id))
info['id'] = video_id
return info