aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/__init__.py2
-rw-r--r--youtube_dl/extractor/cspan.py11
-rw-r--r--youtube_dl/extractor/instagram.py10
-rw-r--r--youtube_dl/extractor/mtv.py7
-rw-r--r--youtube_dl/extractor/orf.py14
-rw-r--r--youtube_dl/extractor/philharmoniedeparis.py78
-rw-r--r--youtube_dl/extractor/southpark.py16
7 files changed, 122 insertions, 16 deletions
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
index a64afa1da..641c45f43 100644
--- a/youtube_dl/extractor/__init__.py
+++ b/youtube_dl/extractor/__init__.py
@@ -377,6 +377,7 @@ from .orf import (
from .parliamentliveuk import ParliamentLiveUKIE
from .patreon import PatreonIE
from .pbs import PBSIE
+from .philharmoniedeparis import PhilharmonieDeParisIE
from .phoenix import PhoenixIE
from .photobucket import PhotobucketIE
from .planetaplay import PlanetaPlayIE
@@ -478,6 +479,7 @@ from .soundgasm import (
)
from .southpark import (
SouthParkIE,
+ SouthParkEsIE,
SouthparkDeIE,
)
from .space import SpaceIE
diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py
index d516b1402..fbefd37d0 100644
--- a/youtube_dl/extractor/cspan.py
+++ b/youtube_dl/extractor/cspan.py
@@ -8,6 +8,7 @@ from ..utils import (
unescapeHTML,
find_xpath_attr,
smuggle_url,
+ determine_ext,
)
from .senateisvp import SenateISVPIE
@@ -87,6 +88,10 @@ class CSpanIE(InfoExtractor):
return self.url_result(surl, 'SenateISVP', video_id, title)
files = data['video']['files']
+ try:
+ capfile = data['video']['capfile']['#text']
+ except KeyError:
+ capfile = None
entries = [{
'id': '%s_%d' % (video_id, partnum + 1),
@@ -97,6 +102,12 @@ class CSpanIE(InfoExtractor):
'description': description,
'thumbnail': thumbnail,
'duration': int_or_none(f.get('length', {}).get('#text')),
+ 'subtitles': {
+ 'en': [{
+ 'url': capfile,
+ 'ext': determine_ext(capfile, 'dfxp')
+ }],
+ } if capfile else None,
} for partnum, f in enumerate(files)]
if len(entries) == 1:
diff --git a/youtube_dl/extractor/instagram.py b/youtube_dl/extractor/instagram.py
index b020e2621..65f6ca103 100644
--- a/youtube_dl/extractor/instagram.py
+++ b/youtube_dl/extractor/instagram.py
@@ -3,13 +3,11 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import (
- int_or_none,
-)
+from ..utils import int_or_none
class InstagramIE(InfoExtractor):
- _VALID_URL = r'http://instagram\.com/p/(?P<id>.*?)/'
+ _VALID_URL = r'https?://instagram\.com/p/(?P<id>[\da-zA-Z]+)'
_TEST = {
'url': 'http://instagram.com/p/aye83DjauH/?foo=bar#abc',
'md5': '0d2da106a9d2631273e192b372806516',
@@ -23,8 +21,8 @@ class InstagramIE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
+ video_id = self._match_id(url)
+
webpage = self._download_webpage(url, video_id)
uploader_id = self._search_regex(r'"owner":{"username":"(.+?)"',
webpage, 'uploader id', fatal=False)
diff --git a/youtube_dl/extractor/mtv.py b/youtube_dl/extractor/mtv.py
index 4430b3416..b48fac5e3 100644
--- a/youtube_dl/extractor/mtv.py
+++ b/youtube_dl/extractor/mtv.py
@@ -25,6 +25,7 @@ def _media_xml_tag(tag):
class MTVServicesInfoExtractor(InfoExtractor):
_MOBILE_TEMPLATE = None
+ _LANG = None
@staticmethod
def _id_from_uri(uri):
@@ -169,8 +170,12 @@ class MTVServicesInfoExtractor(InfoExtractor):
video_id = self._id_from_uri(uri)
feed_url = self._get_feed_url(uri)
data = compat_urllib_parse.urlencode({'uri': uri})
+ info_url = feed_url + '?'
+ if self._LANG:
+ info_url += 'lang=%s&' % self._LANG
+ info_url += data
idoc = self._download_xml(
- feed_url + '?' + data, video_id,
+ info_url, video_id,
'Downloading info', transform_source=fix_xml_ampersands)
return self.playlist_result(
[self._get_video_info(item) for item in idoc.findall('.//item')])
diff --git a/youtube_dl/extractor/orf.py b/youtube_dl/extractor/orf.py
index ca1a5bb3c..2e6c9872b 100644
--- a/youtube_dl/extractor/orf.py
+++ b/youtube_dl/extractor/orf.py
@@ -210,16 +210,16 @@ class ORFIPTVIE(InfoExtractor):
_VALID_URL = r'http://iptv\.orf\.at/(?:#/)?stories/(?P<id>\d+)'
_TEST = {
- 'url': 'http://iptv.orf.at/stories/2267952',
- 'md5': '26ffa4bab6dbce1eee78bbc7021016cd',
+ 'url': 'http://iptv.orf.at/stories/2275236/',
+ 'md5': 'c8b22af4718a4b4af58342529453e3e5',
'info_dict': {
- 'id': '339775',
+ 'id': '350612',
'ext': 'flv',
- 'title': 'Kreml-Kritiker Nawalny wieder frei',
- 'description': 'md5:6f24e7f546d364dacd0e616a9e409236',
- 'duration': 84.729,
+ 'title': 'Weitere Evakuierungen um Vulkan Calbuco',
+ 'description': 'md5:d689c959bdbcf04efeddedbf2299d633',
+ 'duration': 68.197,
'thumbnail': 're:^https?://.*\.jpg$',
- 'upload_date': '20150306',
+ 'upload_date': '20150425',
},
}
diff --git a/youtube_dl/extractor/philharmoniedeparis.py b/youtube_dl/extractor/philharmoniedeparis.py
new file mode 100644
index 000000000..6e60e5fe9
--- /dev/null
+++ b/youtube_dl/extractor/philharmoniedeparis.py
@@ -0,0 +1,78 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+ float_or_none,
+ int_or_none,
+ parse_iso8601,
+ xpath_text,
+)
+
+
+class PhilharmonieDeParisIE(InfoExtractor):
+ IE_DESC = 'Philharmonie de Paris'
+ _VALID_URL = r'http://live\.philharmoniedeparis\.fr/(?:[Cc]oncert/|misc/Playlist\.ashx\?id=)(?P<id>\d+)'
+ _TESTS = [{
+ 'url': 'http://live.philharmoniedeparis.fr/concert/1032066.html',
+ 'info_dict': {
+ 'id': '1032066',
+ 'ext': 'flv',
+ 'title': 'md5:d1f5585d87d041d07ce9434804bc8425',
+ 'timestamp': 1428179400,
+ 'upload_date': '20150404',
+ 'duration': 6592.278,
+ },
+ 'params': {
+ # rtmp download
+ 'skip_download': True,
+ }
+ }, {
+ 'url': 'http://live.philharmoniedeparis.fr/Concert/1030324.html',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://live.philharmoniedeparis.fr/misc/Playlist.ashx?id=1030324&track=&lang=fr',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ concert = self._download_xml(
+ 'http://live.philharmoniedeparis.fr/misc/Playlist.ashx?id=%s' % video_id,
+ video_id).find('./concert')
+
+ formats = []
+ info_dict = {
+ 'id': video_id,
+ 'title': xpath_text(concert, './titre', 'title', fatal=True),
+ 'formats': formats,
+ }
+
+ fichiers = concert.find('./fichiers')
+ stream = fichiers.attrib['serveurstream']
+ for fichier in fichiers.findall('./fichier'):
+ info_dict['duration'] = float_or_none(fichier.get('timecodefin'))
+ for quality, (format_id, suffix) in enumerate([('lq', ''), ('hq', '_hd')]):
+ format_url = fichier.get('url%s' % suffix)
+ if not format_url:
+ continue
+ formats.append({
+ 'url': stream,
+ 'play_path': format_url,
+ 'ext': 'flv',
+ 'format_id': format_id,
+ 'width': int_or_none(concert.get('largeur%s' % suffix)),
+ 'height': int_or_none(concert.get('hauteur%s' % suffix)),
+ 'quality': quality,
+ })
+ self._sort_formats(formats)
+
+ date, hour = concert.get('date'), concert.get('heure')
+ if date and hour:
+ info_dict['timestamp'] = parse_iso8601(
+ '%s-%s-%sT%s:00' % (date[0:4], date[4:6], date[6:8], hour))
+ elif date:
+ info_dict['upload_date'] = date
+
+ return info_dict
diff --git a/youtube_dl/extractor/southpark.py b/youtube_dl/extractor/southpark.py
index c20397b3d..e3b73295c 100644
--- a/youtube_dl/extractor/southpark.py
+++ b/youtube_dl/extractor/southpark.py
@@ -1,3 +1,4 @@
+# encoding: utf-8
from __future__ import unicode_literals
from .mtv import MTVServicesInfoExtractor
@@ -5,7 +6,7 @@ from .mtv import MTVServicesInfoExtractor
class SouthParkIE(MTVServicesInfoExtractor):
IE_NAME = 'southpark.cc.com'
- _VALID_URL = r'https?://(www\.)?(?P<url>southpark\.cc\.com/(clips|full-episodes)/(?P<id>.+?)(\?|#|$))'
+ _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.cc\.com/(?:clips|full-episodes)/(?P<id>.+?)(\?|#|$))'
_FEED_URL = 'http://www.southparkstudios.com/feeds/video-player/mrss'
@@ -20,9 +21,20 @@ class SouthParkIE(MTVServicesInfoExtractor):
}]
+class SouthParkEsIE(SouthParkIE):
+ IE_NAME = 'southpark.cc.com:español'
+ _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.cc\.com/episodios-en-espanol/(?P<id>.+?)(\?|#|$))'
+ _LANG = 'es'
+
+ _TESTS = [{
+ 'url': 'http://southpark.cc.com/episodios-en-espanol/s01e01-cartman-consigue-una-sonda-anal#source=351c1323-0b96-402d-a8b9-40d01b2e9bde&position=1&sort=!airdate',
+ 'playlist_count': 4,
+ }]
+
+
class SouthparkDeIE(SouthParkIE):
IE_NAME = 'southpark.de'
- _VALID_URL = r'https?://(www\.)?(?P<url>southpark\.de/(clips|alle-episoden)/(?P<id>.+?)(\?|#|$))'
+ _VALID_URL = r'https?://(?:www\.)?(?P<url>southpark\.de/(?:clips|alle-episoden)/(?P<id>.+?)(\?|#|$))'
_FEED_URL = 'http://www.southpark.de/feeds/video-player/mrss/'
_TESTS = [{
generated by cgit v1.2.3 (git 2.26.2) at 2025-04-10 14:16:12 +0000