zolfa
/
youtube-dl
1
0
Fork 0
Code Issues 0 Pull Requests 0 Releases 1.1k Wiki Activity
Browse Source

[azmedien] Improve (closes #11784)

master-ytdl-org
Sergey M․ 8 years ago
parent
e84495cd8d
commit
94629e537f
No known key found for this signature in database GPG Key ID: 2C393E0F18A9236D
3 changed files with 135 additions and 90 deletions
Split View
Diff Options
Show Stats Download Patch File Download Diff File
  1. +132
    -0
      youtube_dl/extractor/azmedien.py
  2. +0
    -87
      youtube_dl/extractor/azmedientv.py
  3. +3
    -3
      youtube_dl/extractor/extractors.py

+ 132
- 0
youtube_dl/extractor/azmedien.py View File

@ -0,0 +1,132 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .kaltura import KalturaIE
from ..utils import (
get_element_by_class,
strip_or_none,
)
class AZMedienBaseIE(InfoExtractor):
def _kaltura_video(self, partner_id, entry_id):
return self.url_result(
'kaltura:%s:%s' % (partner_id, entry_id), ie=KalturaIE.ie_key(),
video_id=entry_id)
class AZMedienIE(AZMedienBaseIE):
IE_DESC = 'AZ Medien videos'
_VALID_URL = r'''(?x)
https?://
(?:www\.)?
(?:
telezueri\.ch|
telebaern\.tv|
telem1\.ch
)/
[0-9]+-show-[^/\#]+
(?:
/[0-9]+-episode-[^/\#]+
(?:
/[0-9]+-segment-(?:[^/\#]+\#)?|
\#
)|
\#
)
(?P<id>[^\#]+)
'''
_TESTS = [{
# URL with 'segment'
'url': 'http://www.telezueri.ch/62-show-zuerinews/13772-episode-sonntag-18-dezember-2016/32419-segment-massenabweisungen-beim-hiltl-club-wegen-pelzboom',
'info_dict': {
'id': '1_2444peh4',
'ext': 'mov',
'title': 'Massenabweisungen beim Hiltl Club wegen Pelzboom',
'description': 'md5:9ea9dd1b159ad65b36ddcf7f0d7c76a8',
'uploader_id': 'TeleZ?ri',
'upload_date': '20161218',
'timestamp': 1482084490,
},
'params': {
'skip_download': True,
},
}, {
# URL with 'segment' and fragment:
'url': 'http://www.telebaern.tv/118-show-news/14240-episode-dienstag-17-januar-2017/33666-segment-achtung-gefahr#zu-wenig-pflegerinnen-und-pfleger',
'only_matching': True
}, {
# URL with 'episode' and fragment:
'url': 'http://www.telem1.ch/47-show-sonntalk/13986-episode-soldaten-fuer-grenzschutz-energiestrategie-obama-bilanz#soldaten-fuer-grenzschutz-energiestrategie-obama-bilanz',
'only_matching': True
}, {
# URL with 'show' and fragment:
'url': 'http://www.telezueri.ch/66-show-sonntalk#burka-plakate-trump-putin-china-besuch',
'only_matching': True
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
partner_id = self._search_regex(
r'<script[^>]+src=["\'](?:https?:)?//(?:[^/]+\.)?kaltura\.com(?:/[^/]+)*/(?:p|partner_id)/([0-9]+)',
webpage, 'kaltura partner id')
entry_id = self._html_search_regex(
r'<a[^>]+data-id=(["\'])(?P<id>(?:(?!\1).)+)\1[^>]+data-slug=["\']%s'
% re.escape(video_id), webpage, 'kaltura entry id', group='id')
return self._kaltura_video(partner_id, entry_id)
class AZMedienShowIE(AZMedienBaseIE):
IE_DESC = 'AZ Medien shows'
_VALID_URL = r'https?://(?:www\.)?(?:telezueri\.ch|telebaern\.tv|telem1\.ch)/(?P<id>[0-9]+-show-[^/#]+(?:/[0-9]+-episode-[^/#]+)?)$'
_TESTS = [{
# URL with 'episode'
'url': 'http://www.telebaern.tv/118-show-news/13735-episode-donnerstag-15-dezember-2016',
'info_dict': {
'id': '118-show-news/13735-episode-donnerstag-15-dezember-2016',
'title': 'News - Donnerstag, 15. Dezember 2016',
},
'playlist_count': 9,
}, {
# URL with 'show' only
'url': 'http://www.telezueri.ch/86-show-talktaeglich',
'only_matching': True
}]
def _real_extract(self, url):
show_id = self._match_id(url)
webpage = self._download_webpage(url, show_id)
entries = []
partner_id = self._search_regex(
r'src=["\'](?:https?:)?//(?:[^/]+\.)kaltura\.com/(?:[^/]+/)*(?:p|partner_id)/(\d+)',
webpage, 'kaltura partner id', default=None)
if partner_id:
entries = [
self._kaltura_video(partner_id, m.group('id'))
for m in re.finditer(
r'data-id=(["\'])(?P<id>(?:(?!\1).)+)\1', webpage)]
if not entries:
entries = [
self.url_result(m.group('url'), ie=AZMedienIE.ie_key())
for m in re.finditer(
r'<a[^>]+data-real=(["\'])(?P<url>http.+?)\1', webpage)]
title = self._search_regex(
r'episodeShareTitle\s*=\s*(["\'])(?P<title>(?:(?!\1).)+)\1',
webpage, 'title',
default=strip_or_none(get_element_by_class(
'title-block-cell', webpage)), group='title')
return self.playlist_result(entries, show_id, title)

+ 0
- 87
youtube_dl/extractor/azmedientv.py View File

@ -1,87 +0,0 @@
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from .kaltura import KalturaIE
from ..utils import get_element_by_class
class AZMedienTVIE(InfoExtractor):
IE_DESC = 'telezueri.ch, telebaern.tv and telem1.ch videos'
_VALID_URL = r'http://(?:www\.)?(?:telezueri\.ch|telebaern\.tv|telem1\.ch)/[0-9]+-show-[^/#]+(?:/[0-9]+-episode-[^/#]+(?:/[0-9]+-segment-(?:[^/#]+#)?|#)|#)(?P<id>[^#]+)'
_TESTS = [{
# URL with 'segment'
'url': 'http://www.telezueri.ch/62-show-zuerinews/13772-episode-sonntag-18-dezember-2016/32419-segment-massenabweisungen-beim-hiltl-club-wegen-pelzboom',
'md5': 'fda85ada1299cee517a622bfbc5f6b66',
'info_dict': {
'id': '1_2444peh4',
'ext': 'mov',
'title': 'Massenabweisungen beim Hiltl Club wegen Pelzboom',
'description': 'md5:9ea9dd1b159ad65b36ddcf7f0d7c76a8',
'uploader_id': 'TeleZ?ri',
'upload_date': '20161218',
'timestamp': 1482084490,
}
}, {
# URL with 'segment' and fragment:
'url': 'http://www.telebaern.tv/118-show-news/14240-episode-dienstag-17-januar-2017/33666-segment-achtung-gefahr#zu-wenig-pflegerinnen-und-pfleger',
'only_matching': True
}, {
# URL with 'episode' and fragment:
'url': 'http://www.telem1.ch/47-show-sonntalk/13986-episode-soldaten-fuer-grenzschutz-energiestrategie-obama-bilanz#soldaten-fuer-grenzschutz-energiestrategie-obama-bilanz',
'only_matching': True
}, {
# URL with 'show' and fragment:
'url': 'http://www.telezueri.ch/66-show-sonntalk#burka-plakate-trump-putin-china-besuch',
'only_matching': True
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
kaltura_partner_id = self._html_search_regex(
r'<script[^>]+src=["\']https?://www\.kaltura\.com/.*/partner_id/([0-9]+)',
webpage, 'Kaltura partner ID')
kaltura_entry_id = self._html_search_regex(
r'<a[^>]+data-id=["\'](.*?)["\'][^>]+data-slug=["\']%s' % video_id,
webpage, 'Kaltura entry ID')
return self.url_result(
'kaltura:%s:%s' % (kaltura_partner_id, kaltura_entry_id),
ie=KalturaIE.ie_key())
class AZMedienTVShowIE(InfoExtractor):
IE_DESC = 'telezueri.ch, telebaern.tv and telem1.ch shows'
_VALID_URL = r'http://(?:www\.)?(?:telezueri\.ch|telebaern\.tv|telem1\.ch)/(?P<id>[0-9]+-show-[^/#]+(?:/[0-9]+-episode-[^/#]+)?)$'
_TESTS = [{
# URL with 'episode':
'url': 'http://www.telebaern.tv/118-show-news/13735-episode-donnerstag-15-dezember-2016',
'info_dict': {
'id': '118-show-news/13735-episode-donnerstag-15-dezember-2016',
'title': 'News',
},
'playlist_count': 9,
}, {
# URL with 'show' only:
'url': 'http://www.telezueri.ch/86-show-talktaeglich',
'only_matching': True
}]
def _real_extract(self, url):
show_id = self._match_id(url)
webpage = self._download_webpage(url, show_id)
title = get_element_by_class('title-block-cell', webpage)
if title:
title = title.strip()
entries = [self.url_result(m.group('url'), ie=AZMedienTVIE.ie_key()) for m in re.finditer(
r'<a href=["\']#["\'][^>]+data-real=["\'](?P<url>.+?)["\']', webpage)]
return self.playlist_result(
entries, show_id, title)

+ 3
- 3
youtube_dl/extractor/extractors.py View File

@ -77,9 +77,9 @@ from .awaan import (
AWAANLiveIE,
AWAANSeasonIE,
)
from .azmedientv import (
AZMedienTVIE,
AZMedienTVShowIE,
from .azmedien import (
AZMedienIE,
AZMedienShowIE,
)
from .azubu import AzubuIE, AzubuLiveIE
from .baidu import BaiduVideoIE


Write Preview
Loading…
Cancel
Save