[Viddler] Add support for generic embeds
This commit is contained in:
jgilf
parent
8ae114ea93
commit
e488cfaf0e
@ -1,30 +0,0 @@
|
||||
# coding: utf-8
|
||||
from __future__ import unicode_literals
|
||||
|
||||
from .viddler import ViddlerBaseIE
|
||||
|
||||
|
||||
class BritishCouncilIE(ViddlerBaseIE):
|
||||
_VALID_URL = r'https?://(?:www\.)?(?:learnenglish\.)?britishcouncil.org/(?P<id>.*)'
|
||||
_TEST = {
|
||||
'url': 'https://learnenglish.britishcouncil.org/episode-01-they-meet',
|
||||
'md5': '796e9c4fa07017e3da79d5e99ef36fe8',
|
||||
'info_dict': {
|
||||
'id': '34d5e84c',
|
||||
'ext': 'mp4',
|
||||
'title': 'StartingOut.s01e01',
|
||||
'upload_date': '20160927',
|
||||
'uploader': 'BCLearnenglish',
|
||||
'timestamp': 1474975664,
|
||||
'view_count': int,
|
||||
'comment_count': int,
|
||||
}
|
||||
}
|
||||
|
||||
def _real_extract(self, url):
|
||||
display_id = self._match_id(url)
|
||||
webpage = self._download_webpage(url, display_id)
|
||||
video_id = self._html_search_regex(
|
||||
r'data-video-id=([\'"])(?P<id>[^\'"]+)\1',
|
||||
webpage, 'video ID', group='id', default=None)
|
||||
return self._extract_viddler_info(url, video_id, None)
|
||||
@ -132,7 +132,6 @@ from .brightcove import (
|
||||
BrightcoveLegacyIE,
|
||||
BrightcoveNewIE,
|
||||
)
|
||||
from .britishcouncil import BritishCouncilIE
|
||||
from .businessinsider import BusinessInsiderIE
|
||||
from .buzzfeed import BuzzFeedIE
|
||||
from .byutv import BYUtvIE
|
||||
|
||||
@ -119,6 +119,7 @@ from .expressen import ExpressenIE
|
||||
from .zype import ZypeIE
|
||||
from .odnoklassniki import OdnoklassnikiIE
|
||||
from .kinja import KinjaEmbedIE
|
||||
from .viddler import ViddlerIE
|
||||
|
||||
|
||||
class GenericIE(InfoExtractor):
|
||||
@ -1098,6 +1099,20 @@ class GenericIE(InfoExtractor):
|
||||
},
|
||||
'add_ie': ['Viddler'],
|
||||
},
|
||||
{
|
||||
'url': 'https://learnenglish.britishcouncil.org/episode-01-they-meet',
|
||||
'md5': '796e9c4fa07017e3da79d5e99ef36fe8',
|
||||
'info_dict': {
|
||||
'id': '34d5e84c',
|
||||
'ext': 'mp4',
|
||||
'title': 'StartingOut.s01e01',
|
||||
'upload_date': '20160927',
|
||||
'uploader': 'BCLearnenglish',
|
||||
'timestamp': 1474975664,
|
||||
'view_count': int,
|
||||
'comment_count': int,
|
||||
},
|
||||
},
|
||||
# Libsyn embed
|
||||
{
|
||||
'url': 'http://thedailyshow.cc.com/podcast/episodetwelve',
|
||||
@ -2580,6 +2595,12 @@ class GenericIE(InfoExtractor):
|
||||
if mobj is not None:
|
||||
return self.url_result(mobj.group('url'))
|
||||
|
||||
mobj = re.search(
|
||||
r'<div class="viddler-auto-embed" data-video-id=([\'"])(?P<id>[^\'"]+)\1',
|
||||
webpage)
|
||||
if mobj is not None:
|
||||
return ViddlerIE._build_url_result(mobj.group('id'))
|
||||
|
||||
# Look for NYTimes player
|
||||
mobj = re.search(
|
||||
r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//graphics8\.nytimes\.com/bcvideo/[^/]+/iframe/embed\.html.+?)\1>',
|
||||
|
||||
@ -9,70 +9,7 @@ from ..utils import (
|
||||
)
|
||||
|
||||
|
||||
class ViddlerBaseIE(InfoExtractor):
|
||||
def _extract_viddler_info(self, url, video_id, secret):
|
||||
query = {
|
||||
'video_id': video_id,
|
||||
'key': 'v0vhrt7bg2xq1vyxhkct',
|
||||
}
|
||||
if secret:
|
||||
query['secret'] = secret
|
||||
|
||||
data = self._download_json(
|
||||
'http://api.viddler.com/api/v2/viddler.videos.getPlaybackDetails.json',
|
||||
video_id, headers={'Referer': url}, query=query)['video']
|
||||
|
||||
formats = []
|
||||
for filed in data['files']:
|
||||
if filed.get('status', 'ready') != 'ready':
|
||||
continue
|
||||
format_id = filed.get('profile_id') or filed['profile_name']
|
||||
f = {
|
||||
'format_id': format_id,
|
||||
'format_note': filed['profile_name'],
|
||||
'url': self._proto_relative_url(filed['url']),
|
||||
'width': int_or_none(filed.get('width')),
|
||||
'height': int_or_none(filed.get('height')),
|
||||
'filesize': int_or_none(filed.get('size')),
|
||||
'ext': filed.get('ext'),
|
||||
'source_preference': -1,
|
||||
}
|
||||
formats.append(f)
|
||||
|
||||
if filed.get('cdn_url'):
|
||||
f = f.copy()
|
||||
f['url'] = self._proto_relative_url(filed['cdn_url'], 'http:')
|
||||
f['format_id'] = format_id + '-cdn'
|
||||
f['source_preference'] = 1
|
||||
formats.append(f)
|
||||
|
||||
if filed.get('html5_video_source'):
|
||||
f = f.copy()
|
||||
f['url'] = self._proto_relative_url(filed['html5_video_source'])
|
||||
f['format_id'] = format_id + '-html5'
|
||||
f['source_preference'] = 0
|
||||
formats.append(f)
|
||||
self._sort_formats(formats)
|
||||
|
||||
categories = [
|
||||
t.get('text') for t in data.get('tags', []) if 'text' in t]
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': data['title'],
|
||||
'formats': formats,
|
||||
'description': data.get('description'),
|
||||
'timestamp': int_or_none(data.get('upload_time')),
|
||||
'thumbnail': self._proto_relative_url(data.get('thumbnail_url')),
|
||||
'uploader': data.get('author'),
|
||||
'duration': float_or_none(data.get('length')),
|
||||
'view_count': int_or_none(data.get('view_count')),
|
||||
'comment_count': int_or_none(data.get('comment_count')),
|
||||
'categories': categories,
|
||||
}
|
||||
|
||||
|
||||
class ViddlerIE(ViddlerBaseIE):
|
||||
class ViddlerIE(InfoExtractor):
|
||||
_VALID_URL = r'https?://(?:www\.)?viddler\.com/(?:v|embed|player)/(?P<id>[a-z0-9]+)(?:.+?\bsecret=(\d+))?'
|
||||
_TESTS = [{
|
||||
'url': 'http://www.viddler.com/v/43903784',
|
||||
@ -137,6 +74,74 @@ class ViddlerIE(ViddlerBaseIE):
|
||||
},
|
||||
}]
|
||||
|
||||
@staticmethod
|
||||
def _url_for_id(id):
|
||||
return 'http://www.viddler.com/v/%s' % id
|
||||
|
||||
@classmethod
|
||||
def _build_url_result(cls, id):
|
||||
return cls.url_result(cls._url_for_id(id),
|
||||
ie=cls.ie_key())
|
||||
|
||||
def _real_extract(self, url):
|
||||
video_id, secret = re.match(self._VALID_URL, url).groups()
|
||||
return self._extract_viddler_info(url, video_id, secret)
|
||||
|
||||
query = {
|
||||
'video_id': video_id,
|
||||
'key': 'v0vhrt7bg2xq1vyxhkct',
|
||||
}
|
||||
if secret:
|
||||
query['secret'] = secret
|
||||
|
||||
data = self._download_json(
|
||||
'http://api.viddler.com/api/v2/viddler.videos.getPlaybackDetails.json',
|
||||
video_id, headers={'Referer': url}, query=query)['video']
|
||||
|
||||
formats = []
|
||||
for filed in data['files']:
|
||||
if filed.get('status', 'ready') != 'ready':
|
||||
continue
|
||||
format_id = filed.get('profile_id') or filed['profile_name']
|
||||
f = {
|
||||
'format_id': format_id,
|
||||
'format_note': filed['profile_name'],
|
||||
'url': self._proto_relative_url(filed['url']),
|
||||
'width': int_or_none(filed.get('width')),
|
||||
'height': int_or_none(filed.get('height')),
|
||||
'filesize': int_or_none(filed.get('size')),
|
||||
'ext': filed.get('ext'),
|
||||
'source_preference': -1,
|
||||
}
|
||||
formats.append(f)
|
||||
|
||||
if filed.get('cdn_url'):
|
||||
f = f.copy()
|
||||
f['url'] = self._proto_relative_url(filed['cdn_url'], 'http:')
|
||||
f['format_id'] = format_id + '-cdn'
|
||||
f['source_preference'] = 1
|
||||
formats.append(f)
|
||||
|
||||
if filed.get('html5_video_source'):
|
||||
f = f.copy()
|
||||
f['url'] = self._proto_relative_url(filed['html5_video_source'])
|
||||
f['format_id'] = format_id + '-html5'
|
||||
f['source_preference'] = 0
|
||||
formats.append(f)
|
||||
self._sort_formats(formats)
|
||||
|
||||
categories = [
|
||||
t.get('text') for t in data.get('tags', []) if 'text' in t]
|
||||
|
||||
return {
|
||||
'id': video_id,
|
||||
'title': data['title'],
|
||||
'formats': formats,
|
||||
'description': data.get('description'),
|
||||
'timestamp': int_or_none(data.get('upload_time')),
|
||||
'thumbnail': self._proto_relative_url(data.get('thumbnail_url')),
|
||||
'uploader': data.get('author'),
|
||||
'duration': float_or_none(data.get('length')),
|
||||
'view_count': int_or_none(data.get('view_count')),
|
||||
'comment_count': int_or_none(data.get('comment_count')),
|
||||
'categories': categories,
|
||||
}
|
||||
|
||||
Loading…
x
Reference in New Issue
Block a user