+# -*- coding: utf-8 -*-
from __future__ import unicode_literals
+import itertools
import re
from .common import InfoExtractor
-from ..utils import (
- unified_strdate,
+from ..compat import (
+ compat_parse_qs,
compat_urlparse,
+)
+from ..utils import (
determine_ext,
+ unified_strdate,
)
},
},
{
- 'url': 'http://www.funkhauseuropa.de/av/audiogrenzenlosleckerbaklava101-audioplayer.html',
- 'md5': 'cfff440d4ee64114083ac44676df5d15',
+ 'url': 'http://www.funkhauseuropa.de/av/audioflaviacoelhoamaramar100-audioplayer.html',
+ 'md5': '99a1443ff29af19f6c52cf6f4dc1f4aa',
'info_dict': {
- 'id': 'mdb-363068',
+ 'id': 'mdb-478135',
'ext': 'mp3',
- 'title': 'Grenzenlos lecker - Baklava',
+ 'title': 'Flavia Coelho: Amar é Amar',
'description': 'md5:7b29e97e10dfb6e265238b32fa35b23a',
- 'upload_date': '20140311',
+ 'upload_date': '20140717',
},
},
+ {
+ 'url': 'http://www1.wdr.de/mediathek/video/sendungen/quarks_und_co/filterseite-quarks-und-co100.html',
+ 'playlist_mincount': 146,
+ }
]
def _real_extract(self, url):
self.url_result(page_url + href, 'WDR')
for href in re.findall(r'<a href="/?(.+?%s\.html)" rel="nofollow"' % self._PLAYER_REGEX, webpage)
]
+
+ if entries: # Playlist page
+ return self.playlist_result(entries, page_id)
+
+ # Overview page
+ entries = []
+ for page_num in itertools.count(2):
+ hrefs = re.findall(
+ r'<li class="mediathekvideo"\s*>\s*<img[^>]*>\s*<a href="(/mediathek/video/[^"]+)"',
+ webpage)
+ entries.extend(
+ self.url_result(page_url + href, 'WDR')
+ for href in hrefs)
+ next_url_m = re.search(
+ r'<li class="nextToLast">\s*<a href="([^"]+)"', webpage)
+ if not next_url_m:
+ break
+ next_url = page_url + next_url_m.group(1)
+ webpage = self._download_webpage(
+ next_url, page_id,
+ note='Downloading playlist page %d' % page_num)
return self.playlist_result(entries, page_id)
- flashvars = compat_urlparse.parse_qs(
+ flashvars = compat_parse_qs(
self._html_search_regex(r'<param name="flashvars" value="([^"]+)"', webpage, 'flashvars'))
page_id = flashvars['trackerClipId'][0]
'description': description,
'thumbnail': thumbnail,
'upload_date': upload_date,
- }
\ No newline at end of file
+ }
+
+
+class WDRMobileIE(InfoExtractor):
+ _VALID_URL = r'''(?x)
+ https?://mobile-ondemand\.wdr\.de/
+ .*?/fsk(?P<age_limit>[0-9]+)
+ /[0-9]+/[0-9]+/
+ (?P<id>[0-9]+)_(?P<title>[0-9]+)'''
+ IE_NAME = 'wdr:mobile'
+ _TEST = {
+ 'url': 'http://mobile-ondemand.wdr.de/CMS2010/mdb/ondemand/weltweit/fsk0/42/421735/421735_4283021.mp4',
+ 'info_dict': {
+ 'title': '4283021',
+ 'id': '421735',
+ 'ext': 'mp4',
+ 'age_limit': 0,
+ },
+ 'skip': 'Problems with loading data.'
+ }
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ return {
+ 'id': mobj.group('id'),
+ 'title': mobj.group('title'),
+ 'age_limit': int(mobj.group('age_limit')),
+ 'url': url,
+ 'http_headers': {
+ 'User-Agent': 'mobile',
+ },
+ }
+
+
+class WDRMausIE(InfoExtractor):
+ _VALID_URL = 'http://(?:www\.)?wdrmaus\.de/(?:[^/]+/){,2}(?P<id>[^/?#]+)(?:/index\.php5|(?<!index)\.php5|/(?:$|[?#]))'
+ IE_DESC = 'Sendung mit der Maus'
+ _TESTS = [{
+ 'url': 'http://www.wdrmaus.de/aktuelle-sendung/index.php5',
+ 'info_dict': {
+ 'id': 'aktuelle-sendung',
+ 'ext': 'mp4',
+ 'thumbnail': 're:^http://.+\.jpg',
+ 'upload_date': 're:^[0-9]{8}$',
+ 'title': 're:^[0-9.]{10} - Aktuelle Sendung$',
+ }
+ }, {
+ 'url': 'http://www.wdrmaus.de/sachgeschichten/sachgeschichten/40_jahre_maus.php5',
+ 'md5': '3b1227ca3ed28d73ec5737c65743b2a3',
+ 'info_dict': {
+ 'id': '40_jahre_maus',
+ 'ext': 'mp4',
+ 'thumbnail': 're:^http://.+\.jpg',
+ 'upload_date': '20131007',
+ 'title': '12.03.2011 - 40 Jahre Maus',
+ }
+ }]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, video_id)
+ param_code = self._html_search_regex(
+ r'<a href="\?startVideo=1&([^"]+)"', webpage, 'parameters')
+
+ title_date = self._search_regex(
+ r'<div class="sendedatum"><p>Sendedatum:\s*([0-9\.]+)</p>',
+ webpage, 'air date')
+ title_str = self._html_search_regex(
+ r'<h1>(.*?)</h1>', webpage, 'title')
+ title = '%s - %s' % (title_date, title_str)
+ upload_date = unified_strdate(
+ self._html_search_meta('dc.date', webpage))
+
+ fields = compat_parse_qs(param_code)
+ video_url = fields['firstVideo'][0]
+ thumbnail = compat_urlparse.urljoin(url, fields['startPicture'][0])
+
+ formats = [{
+ 'format_id': 'rtmp',
+ 'url': video_url,
+ }]
+
+ jscode = self._download_webpage(
+ 'http://www.wdrmaus.de/codebase/js/extended-medien.min.js',
+ video_id, fatal=False,
+ note='Downloading URL translation table',
+ errnote='Could not download URL translation table')
+ if jscode:
+ for m in re.finditer(
+ r"stream:\s*'dslSrc=(?P<stream>[^']+)',\s*download:\s*'(?P<dl>[^']+)'\s*\}",
+ jscode):
+ if video_url.startswith(m.group('stream')):
+ http_url = video_url.replace(
+ m.group('stream'), m.group('dl'))
+ formats.append({
+ 'format_id': 'http',
+ 'url': http_url,
+ })
+ break
+
+ self._sort_formats(formats)
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'formats': formats,
+ 'thumbnail': thumbnail,
+ 'upload_date': upload_date,
+ }
projects / youtube-dl / blobdiff