aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/iprima.py16
-rw-r--r--youtube_dl/extractor/tumblr.py17
-rw-r--r--youtube_dl/extractor/tvigle.py10
-rw-r--r--youtube_dl/extractor/twentyfourvideo.py4
-rw-r--r--youtube_dl/extractor/vidme.py9
5 files changed, 46 insertions, 10 deletions
diff --git a/youtube_dl/extractor/iprima.py b/youtube_dl/extractor/iprima.py
index 8529bedfc..821c8ec10 100644
--- a/youtube_dl/extractor/iprima.py
+++ b/youtube_dl/extractor/iprima.py
@@ -11,11 +11,12 @@ from ..compat import (
)
from ..utils import (
ExtractorError,
+ remove_end,
)
class IPrimaIE(InfoExtractor):
- _VALID_URL = r'https?://play\.iprima\.cz/[^?#]+/(?P<id>[^?#]+)'
+ _VALID_URL = r'https?://play\.iprima\.cz/(?:[^/]+/)*(?P<id>[^?#]+)'
_TESTS = [{
'url': 'http://play.iprima.cz/particka/particka-92',
@@ -23,7 +24,7 @@ class IPrimaIE(InfoExtractor):
'id': '39152',
'ext': 'flv',
'title': 'Partička (92)',
- 'description': 'md5:3740fda51464da35a2d4d0670b8e4fd6',
+ 'description': 'md5:74e9617e51bca67c3ecfb2c6f9766f45',
'thumbnail': 'http://play.iprima.cz/sites/default/files/image_crops/image_620x349/3/491483_particka-92_image_620x349.jpg',
},
'params': {
@@ -35,13 +36,14 @@ class IPrimaIE(InfoExtractor):
'id': '9718337',
'ext': 'flv',
'title': 'Tchibo Partička - Jarní móda',
- 'description': 'md5:589f8f59f414220621ff8882eb3ce7be',
'thumbnail': 're:^http:.*\.jpg$',
},
'params': {
'skip_download': True, # requires rtmpdump
},
- 'skip': 'Do not have permission to access this page',
+ }, {
+ 'url': 'http://play.iprima.cz/zpravy-ftv-prima-2752015',
+ 'only_matching': True,
}]
def _real_extract(self, url):
@@ -102,8 +104,10 @@ class IPrimaIE(InfoExtractor):
return {
'id': real_id,
- 'title': self._og_search_title(webpage),
+ 'title': remove_end(self._og_search_title(webpage), ' | Prima PLAY'),
'thumbnail': self._og_search_thumbnail(webpage),
'formats': formats,
- 'description': self._og_search_description(webpage),
+ 'description': self._search_regex(
+ r'<p[^>]+itemprop="description"[^>]*>([^<]+)',
+ webpage, 'description', default=None),
}
diff --git a/youtube_dl/extractor/tumblr.py b/youtube_dl/extractor/tumblr.py
index 828c808a6..e6218808f 100644
--- a/youtube_dl/extractor/tumblr.py
+++ b/youtube_dl/extractor/tumblr.py
@@ -28,6 +28,17 @@ class TumblrIE(InfoExtractor):
'description': 'md5:dba62ac8639482759c8eb10ce474586a',
'thumbnail': 're:http://.*\.jpg',
}
+ }, {
+ 'url': 'http://naked-yogi.tumblr.com/post/118312946248/naked-smoking-stretching',
+ 'md5': 'de07e5211d60d4f3a2c3df757ea9f6ab',
+ 'info_dict': {
+ 'id': 'Wmur',
+ 'ext': 'mp4',
+ 'title': 'naked smoking & stretching',
+ 'upload_date': '20150506',
+ 'timestamp': 1430931613,
+ },
+ 'add_ie': ['Vidme'],
}]
def _real_extract(self, url):
@@ -38,6 +49,12 @@ class TumblrIE(InfoExtractor):
url = 'http://%s.tumblr.com/post/%s/' % (blog, video_id)
webpage = self._download_webpage(url, video_id)
+ vid_me_embed_url = self._search_regex(
+ r'src=[\'"](https?://vid\.me/[^\'"]+)[\'"]',
+ webpage, 'vid.me embed', default=None)
+ if vid_me_embed_url is not None:
+ return self.url_result(vid_me_embed_url, 'Vidme')
+
iframe_url = self._search_regex(
r'src=\'(https?://www\.tumblr\.com/video/[^\']+)\'',
webpage, 'iframe url')
diff --git a/youtube_dl/extractor/tvigle.py b/youtube_dl/extractor/tvigle.py
index a85693888..dc3a8334a 100644
--- a/youtube_dl/extractor/tvigle.py
+++ b/youtube_dl/extractor/tvigle.py
@@ -5,6 +5,7 @@ import re
from .common import InfoExtractor
from ..utils import (
+ ExtractorError,
float_or_none,
int_or_none,
parse_age_limit,
@@ -29,6 +30,7 @@ class TvigleIE(InfoExtractor):
'duration': 6586,
'age_limit': 12,
},
+ 'skip': 'georestricted',
},
{
'url': 'http://www.tvigle.ru/video/vladimir-vysotskii/vedushchii-teleprogrammy-60-minut-ssha-o-vladimire-vysotskom/',
@@ -41,6 +43,7 @@ class TvigleIE(InfoExtractor):
'duration': 186.080,
'age_limit': 0,
},
+ 'skip': 'georestricted',
}, {
'url': 'https://cloud.tvigle.ru/video/5267604/',
'only_matching': True,
@@ -63,6 +66,13 @@ class TvigleIE(InfoExtractor):
item = video_data['playlist']['items'][0]
+ videos = item.get('videos')
+
+ error_message = item.get('errorMessage')
+ if not videos and error_message:
+ raise ExtractorError(
+ '%s returned error: %s' % (self.IE_NAME, error_message), expected=True)
+
title = item['title']
description = item.get('description')
thumbnail = item.get('thumbnail')
diff --git a/youtube_dl/extractor/twentyfourvideo.py b/youtube_dl/extractor/twentyfourvideo.py
index 67e8bfea0..c1ee1decc 100644
--- a/youtube_dl/extractor/twentyfourvideo.py
+++ b/youtube_dl/extractor/twentyfourvideo.py
@@ -15,7 +15,7 @@ class TwentyFourVideoIE(InfoExtractor):
_TESTS = [
{
'url': 'http://www.24video.net/video/view/1044982',
- 'md5': '48dd7646775690a80447a8dca6a2df76',
+ 'md5': 'd041af8b5b4246ea466226a0d6693345',
'info_dict': {
'id': '1044982',
'ext': 'mp4',
@@ -54,7 +54,7 @@ class TwentyFourVideoIE(InfoExtractor):
webpage, 'upload date'))
uploader = self._html_search_regex(
- r'Загрузил\s*<a href="/jsecUser/movies/[^"]+" class="link">([^<]+)</a>',
+ r'class="video-uploaded"[^>]*>\s*<a href="/jsecUser/movies/[^"]+"[^>]*>([^<]+)</a>',
webpage, 'uploader', fatal=False)
view_count = int_or_none(self._html_search_regex(
diff --git a/youtube_dl/extractor/vidme.py b/youtube_dl/extractor/vidme.py
index bd953fb4c..e0b55078b 100644
--- a/youtube_dl/extractor/vidme.py
+++ b/youtube_dl/extractor/vidme.py
@@ -10,7 +10,7 @@ from ..utils import (
class VidmeIE(InfoExtractor):
_VALID_URL = r'https?://vid\.me/(?:e/)?(?P<id>[\da-zA-Z]+)'
- _TEST = {
+ _TESTS = [{
'url': 'https://vid.me/QNB',
'md5': 'f42d05e7149aeaec5c037b17e5d3dc82',
'info_dict': {
@@ -23,9 +23,14 @@ class VidmeIE(InfoExtractor):
'upload_date': '20140725',
'thumbnail': 're:^https?://.*\.jpg',
},
- }
+ }, {
+ # From http://naked-yogi.tumblr.com/post/118312946248/naked-smoking-stretching
+ 'url': 'https://vid.me/e/Wmur',
+ 'only_matching': True,
+ }]
def _real_extract(self, url):
+ url = url.replace('vid.me/e/', 'vid.me/')
video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id)
generated by cgit v1.2.3 (git 2.26.2) at 2025-04-05 12:12:39 +0000