commit 7d11297f3f91e6ddd3f0caa5ad4dca1a40d6c820
parent 6ad4013d40e839211e2896129eed05ccd40ee963
Author: Philipp Hagemeister <phihag@phihag.de>
Date: Wed, 29 Oct 2014 20:10:07 +0100
Merge branch 'master' of github.com:rg3/youtube-dl
Diffstat:
5 files changed, 62 insertions(+), 24 deletions(-)
diff --git a/test/test_utils.py b/test/test_utils.py
@@ -361,12 +361,14 @@ class TestUtil(unittest.TestCase):
def test_compat_getenv(self):
test_str = 'тест'
- os.environ['YOUTUBE-DL-TEST'] = test_str.encode(get_filesystem_encoding())
+ os.environ['YOUTUBE-DL-TEST'] = (test_str if sys.version_info >= (3, 0)
+ else test_str.encode(get_filesystem_encoding()))
self.assertEqual(compat_getenv('YOUTUBE-DL-TEST'), test_str)
def test_compat_expanduser(self):
test_str = 'C:\Documents and Settings\тест\Application Data'
- os.environ['HOME'] = test_str.encode(get_filesystem_encoding())
+ os.environ['HOME'] = (test_str if sys.version_info >= (3, 0)
+ else test_str.encode(get_filesystem_encoding()))
self.assertEqual(compat_expanduser('~'), test_str)
if __name__ == '__main__':
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
@@ -252,7 +252,7 @@ from .newstube import NewstubeIE
from .nfb import NFBIE
from .nfl import NFLIE
from .nhl import NHLIE, NHLVideocenterIE
-from .niconico import NiconicoIE
+from .niconico import NiconicoIE, NiconicoPlaylistIE
from .ninegag import NineGagIE
from .noco import NocoIE
from .normalboots import NormalbootsIE
diff --git a/youtube_dl/extractor/naver.py b/youtube_dl/extractor/naver.py
@@ -7,6 +7,7 @@ from .common import InfoExtractor
from ..utils import (
compat_urllib_parse,
ExtractorError,
+ clean_html,
)
@@ -31,6 +32,11 @@ class NaverIE(InfoExtractor):
m_id = re.search(r'var rmcPlayer = new nhn.rmcnmv.RMCVideoPlayer\("(.+?)", "(.+?)"',
webpage)
if m_id is None:
+ m_error = re.search(
+ r'(?s)<div class="nation_error">\s*(?:<!--.*?-->)?\s*<p class="[^"]+">(?P<msg>.+?)</p>\s*</div>',
+ webpage)
+ if m_error:
+ raise ExtractorError(clean_html(m_error.group('msg')), expected=True)
raise ExtractorError('couldn\'t extract vid and key')
vid = m_id.group(1)
key = m_id.group(2)
diff --git a/youtube_dl/extractor/niconico.py b/youtube_dl/extractor/niconico.py
@@ -2,6 +2,7 @@
from __future__ import unicode_literals
import re
+import json
from .common import InfoExtractor
from ..utils import (
@@ -146,3 +147,36 @@ class NiconicoIE(InfoExtractor):
'duration': duration,
'webpage_url': webpage_url,
}
+
+
+class NiconicoPlaylistIE(InfoExtractor):
+ _VALID_URL = r'https?://www\.nicovideo\.jp/mylist/(?P<id>\d+)'
+
+ _TEST = {
+ 'url': 'http://www.nicovideo.jp/mylist/27411728',
+ 'info_dict': {
+ 'id': '27411728',
+ 'title': 'AKB48のオールナイトニッポン',
+ },
+ 'playlist_mincount': 225,
+ }
+
+ def _real_extract(self, url):
+ list_id = self._match_id(url)
+ webpage = self._download_webpage(url, list_id)
+
+ entries_json = self._search_regex(r'Mylist\.preload\(\d+, (\[.*\])\);',
+ webpage, 'entries')
+ entries = json.loads(entries_json)
+ entries = [{
+ '_type': 'url',
+ 'ie_key': NiconicoIE.ie_key(),
+ 'url': 'http://www.nicovideo.jp/watch/%s' % entry['item_id'],
+ } for entry in entries]
+
+ return {
+ '_type': 'playlist',
+ 'title': self._search_regex(r'\s+name: "(.*?)"', webpage, 'title'),
+ 'id': list_id,
+ 'entries': entries,
+ }
diff --git a/youtube_dl/extractor/trutube.py b/youtube_dl/extractor/trutube.py
@@ -1,13 +1,12 @@
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
+from ..utils import xpath_text
class TruTubeIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?trutube\.tv/video/(?P<id>[0-9]+)/.*'
- _TEST = {
+ _VALID_URL = r'https?://(?:www\.)?trutube\.tv/(?:video/|nuevo/player/embed\.php\?v=)(?P<id>[0-9]+)'
+ _TESTS = [{
'url': 'http://trutube.tv/video/14880/Ramses-II-Proven-To-Be-A-Red-Headed-Caucasoid-',
'md5': 'c5b6e301b0a2040b074746cbeaa26ca1',
'info_dict': {
@@ -16,29 +15,26 @@ class TruTubeIE(InfoExtractor):
'title': 'Ramses II - Proven To Be A Red Headed Caucasoid',
'thumbnail': 're:^http:.*\.jpg$',
}
- }
+ }, {
+ 'url': 'https://trutube.tv/nuevo/player/embed.php?v=14880',
+ 'only_matching': True,
+ }]
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)
- video_title = self._og_search_title(webpage).strip()
- thumbnail = self._search_regex(
- r"var splash_img = '([^']+)';", webpage, 'thumbnail', fatal=False)
+ config = self._download_xml(
+ 'https://trutube.tv/nuevo/player/config.php?v=%s' % video_id,
+ video_id, transform_source=lambda s: s.strip())
- all_formats = re.finditer(
- r"var (?P<key>[a-z]+)_video_file\s*=\s*'(?P<url>[^']+)';", webpage)
- formats = [{
- 'format_id': m.group('key'),
- 'quality': -i,
- 'url': m.group('url'),
- } for i, m in enumerate(all_formats)]
- self._sort_formats(formats)
+ # filehd is always 404
+ video_url = xpath_text(config, './file', 'video URL', fatal=True)
+ title = xpath_text(config, './title', 'title')
+ thumbnail = xpath_text(config, './image', ' thumbnail')
return {
'id': video_id,
- 'title': video_title,
- 'formats': formats,
+ 'url': video_url,
+ 'title': title,
'thumbnail': thumbnail,
}
