commit 2396062c747ee81420dac0eac914d531ec8df910
parent 14704aeff6eeee4357e3a26f83432ff908db64fc
Author: Remita Amine <remitamine@gmail.com>
Date: Thu, 4 Aug 2016 16:21:27 +0100
[5min] delegate extraction to AolIE
recently the 5min SenseHandler request return
HTTP Error 503: Service Unavailable error
Diffstat:
1 file changed, 19 insertions(+), 116 deletions(-)
diff --git a/youtube_dl/extractor/fivemin.py b/youtube_dl/extractor/fivemin.py
@@ -1,24 +1,11 @@
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
-from ..compat import (
- compat_parse_qs,
- compat_urllib_parse_urlencode,
- compat_urllib_parse_urlparse,
- compat_urlparse,
-)
-from ..utils import (
- ExtractorError,
- parse_duration,
- replace_extension,
-)
class FiveMinIE(InfoExtractor):
IE_NAME = '5min'
- _VALID_URL = r'(?:5min:(?P<id>\d+)(?::(?P<sid>\d+))?|https?://[^/]*?5min\.com/Scripts/PlayerSeed\.js\?(?P<query>.*))'
+ _VALID_URL = r'(?:5min:|(?:https?://(?:[^/]*?5min\.com|delivery\.vidible\.tv/aol)/(?:(?:Scripts/PlayerSeed\.js|playerseed/?)?\?.*?playList=)?)(?P<id>\d+)'
_TESTS = [
{
@@ -29,8 +16,16 @@ class FiveMinIE(InfoExtractor):
'id': '518013791',
'ext': 'mp4',
'title': 'iPad Mini with Retina Display Review',
+ 'description': 'iPad mini with Retina Display review',
'duration': 177,
+ 'uploader': 'engadget',
+ 'upload_date': '20131115',
+ 'timestamp': 1384515288,
},
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ }
},
{
# From http://on.aol.com/video/how-to-make-a-next-level-fruit-salad-518086247
@@ -44,108 +39,16 @@ class FiveMinIE(InfoExtractor):
},
'skip': 'no longer available',
},
- ]
- _ERRORS = {
- 'ErrorVideoNotExist': 'We\'re sorry, but the video you are trying to watch does not exist.',
- 'ErrorVideoNoLongerAvailable': 'We\'re sorry, but the video you are trying to watch is no longer available.',
- 'ErrorVideoRejected': 'We\'re sorry, but the video you are trying to watch has been removed.',
- 'ErrorVideoUserNotGeo': 'We\'re sorry, but the video you are trying to watch cannot be viewed from your current location.',
- 'ErrorVideoLibraryRestriction': 'We\'re sorry, but the video you are trying to watch is currently unavailable for viewing at this domain.',
- 'ErrorExposurePermission': 'We\'re sorry, but the video you are trying to watch is currently unavailable for viewing at this domain.',
- }
- _QUALITIES = {
- 1: {
- 'width': 640,
- 'height': 360,
- },
- 2: {
- 'width': 854,
- 'height': 480,
- },
- 4: {
- 'width': 1280,
- 'height': 720,
- },
- 8: {
- 'width': 1920,
- 'height': 1080,
- },
- 16: {
- 'width': 640,
- 'height': 360,
- },
- 32: {
- 'width': 854,
- 'height': 480,
- },
- 64: {
- 'width': 1280,
- 'height': 720,
- },
- 128: {
- 'width': 640,
- 'height': 360,
+ {
+ 'url': 'http://embed.5min.com/518726732/',
+ 'only_matching': True,
},
- }
+ {
+ 'url': 'http://delivery.vidible.tv/aol?playList=518013791',
+ 'only_matching': True,
+ }
+ ]
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
- sid = mobj.group('sid')
-
- if mobj.group('query'):
- qs = compat_parse_qs(mobj.group('query'))
- if not qs.get('playList'):
- raise ExtractorError('Invalid URL', expected=True)
- video_id = qs['playList'][0]
- if qs.get('sid'):
- sid = qs['sid'][0]
-
- embed_url = 'https://embed.5min.com/playerseed/?playList=%s' % video_id
- if not sid:
- embed_page = self._download_webpage(embed_url, video_id,
- 'Downloading embed page')
- sid = self._search_regex(r'sid=(\d+)', embed_page, 'sid')
-
- response = self._download_json(
- 'https://syn.5min.com/handlers/SenseHandler.ashx?' +
- compat_urllib_parse_urlencode({
- 'func': 'GetResults',
- 'playlist': video_id,
- 'sid': sid,
- 'isPlayerSeed': 'true',
- 'url': embed_url,
- }),
- video_id)
- if not response['success']:
- raise ExtractorError(
- '%s said: %s' % (
- self.IE_NAME,
- self._ERRORS.get(response['errorMessage'], response['errorMessage'])),
- expected=True)
- info = response['binding'][0]
-
- formats = []
- parsed_video_url = compat_urllib_parse_urlparse(compat_parse_qs(
- compat_urllib_parse_urlparse(info['EmbededURL']).query)['videoUrl'][0])
- for rendition in info['Renditions']:
- if rendition['RenditionType'] == 'aac' or rendition['RenditionType'] == 'm3u8':
- continue
- else:
- rendition_url = compat_urlparse.urlunparse(parsed_video_url._replace(path=replace_extension(parsed_video_url.path.replace('//', '/%s/' % rendition['ID']), rendition['RenditionType'])))
- quality = self._QUALITIES.get(rendition['ID'], {})
- formats.append({
- 'format_id': '%s-%d' % (rendition['RenditionType'], rendition['ID']),
- 'url': rendition_url,
- 'width': quality.get('width'),
- 'height': quality.get('height'),
- })
- self._sort_formats(formats)
-
- return {
- 'id': video_id,
- 'title': info['Title'],
- 'thumbnail': info.get('ThumbURL'),
- 'duration': parse_duration(info.get('Duration')),
- 'formats': formats,
- }
+ video_id = self._match_id(url)
+ return self.url_result('aol-video:%s' % video_id)
