Merge branch 'master' of github.com:rg3/youtube-dl

This commit is contained in:
Philipp Hagemeister 2014-12-04 17:02:14 +01:00
commit 7e26084d09
3 changed files with 112 additions and 10 deletions

View File

@ -122,6 +122,7 @@ from .flickr import FlickrIE
from .folketinget import FolketingetIE from .folketinget import FolketingetIE
from .fourtube import FourTubeIE from .fourtube import FourTubeIE
from .foxgay import FoxgayIE from .foxgay import FoxgayIE
from .foxnews import FoxNewsIE
from .franceculture import FranceCultureIE from .franceculture import FranceCultureIE
from .franceinter import FranceInterIE from .franceinter import FranceInterIE
from .francetv import ( from .francetv import (

View File

@ -0,0 +1,94 @@
from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
parse_iso8601,
int_or_none,
)
class FoxNewsIE(InfoExtractor):
_VALID_URL = r'https?://video\.foxnews\.com/v/(?:video-embed\.html\?video_id=)?(?P<id>\d+)'
_TESTS = [
{
'url': 'http://video.foxnews.com/v/3937480/frozen-in-time/#sp=show-clips',
'md5': '32aaded6ba3ef0d1c04e238d01031e5e',
'info_dict': {
'id': '3937480',
'ext': 'flv',
'title': 'Frozen in Time',
'description': 'Doctors baffled by 16-year-old girl that is the size of a toddler',
'duration': 265,
'timestamp': 1304411491,
'upload_date': '20110503',
'thumbnail': 're:^https?://.*\.jpg$',
},
},
{
'url': 'http://video.foxnews.com/v/3922535568001/rep-luis-gutierrez-on-if-obamas-immigration-plan-is-legal/#sp=show-clips',
'md5': '5846c64a1ea05ec78175421b8323e2df',
'info_dict': {
'id': '3922535568001',
'ext': 'mp4',
'title': "Rep. Luis Gutierrez on if Obama's immigration plan is legal",
'description': "Congressman discusses the president's executive action",
'duration': 292,
'timestamp': 1417662047,
'upload_date': '20141204',
'thumbnail': 're:^https?://.*\.jpg$',
},
},
{
'url': 'http://video.foxnews.com/v/video-embed.html?video_id=3937480&d=video.foxnews.com',
'only_matching': True,
},
]
def _real_extract(self, url):
video_id = self._match_id(url)
video = self._download_json(
'http://video.foxnews.com/v/feed/video/%s.js?template=fox' % 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,
}

View File

@ -63,29 +63,36 @@ class VineIE(InfoExtractor):
class VineUserIE(InfoExtractor): class VineUserIE(InfoExtractor):
IE_NAME = 'vine:user' IE_NAME = 'vine:user'
_VALID_URL = r'(?:https?://)?vine\.co/(?P<user>[^/]+)/?(\?.*)?$' _VALID_URL = r'(?:https?://)?vine\.co/(?P<u>u/)?(?P<user>[^/]+)/?(\?.*)?$'
_VINE_BASE_URL = "https://vine.co/" _VINE_BASE_URL = "https://vine.co/"
_TEST = { _TESTS = [
'url': 'https://vine.co/Visa', {
'info_dict': { 'url': 'https://vine.co/Visa',
'id': 'Visa', 'info_dict': {
'id': 'Visa',
},
'playlist_mincount': 46,
}, },
'playlist_mincount': 46, {
} 'url': 'https://vine.co/u/941705360593584128',
'only_matching': True,
},
]
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
user = mobj.group('user') user = mobj.group('user')
u = mobj.group('u')
profile_url = "%sapi/users/profiles/vanity/%s" % ( profile_url = "%sapi/users/profiles/%s%s" % (
self._VINE_BASE_URL, user) self._VINE_BASE_URL, 'vanity/' if not u else '', user)
profile_data = self._download_json( profile_data = self._download_json(
profile_url, user, note='Downloading user profile data') profile_url, user, note='Downloading user profile data')
user_id = profile_data['data']['userId'] user_id = profile_data['data']['userId']
timeline_data = [] timeline_data = []
for pagenum in itertools.count(1): for pagenum in itertools.count(1):
timeline_url = "%sapi/timelines/users/%s?page=%s" % ( timeline_url = "%sapi/timelines/users/%s?page=%s&size=100" % (
self._VINE_BASE_URL, user_id, pagenum) self._VINE_BASE_URL, user_id, pagenum)
timeline_page = self._download_json( timeline_page = self._download_json(
timeline_url, user, note='Downloading page %d' % pagenum) timeline_url, user, note='Downloading page %d' % pagenum)