aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/shared.py
diff options
context:
space:
mode:
authorPhilipp Hagemeister <phihag@phihag.de>2014-12-13 12:24:42 +0100
committerPhilipp Hagemeister <phihag@phihag.de>2014-12-13 12:35:45 +0100
commit1cc79574fc5df21bf35dccf61eac0e9e75ed8d20 (patch)
tree5cc2bd2a2faba0ac5e8371892e3ef09ab5338080 /youtube_dl/extractor/shared.py
parent20e35880bf7413c5085c1ade96af0fc6e56d84d1 (diff)
Fix imports and general cleanup
· Import from compat what comes from compat. Yes, some names are available in utils too, but that's an implementation detail. · Use _match_id consistently whenever possible · Fix some outdated tests · Use consistent valid URL (always match the whole protocol, no ^ at start required) · Use modern test definitions
Diffstat (limited to 'youtube_dl/extractor/shared.py')
-rw-r--r--youtube_dl/extractor/shared.py38
1 files changed, 22 insertions, 16 deletions
diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py
index fdc31603a..26ced716e 100644
--- a/youtube_dl/extractor/shared.py
+++ b/youtube_dl/extractor/shared.py
@@ -4,10 +4,12 @@ import re
import base64
from .common import InfoExtractor
+from ..compat import (
+ compat_urllib_parse,
+ compat_urllib_request,
+)
from ..utils import (
ExtractorError,
- compat_urllib_request,
- compat_urllib_parse,
int_or_none,
)
@@ -26,26 +28,30 @@ class SharedIE(InfoExtractor):
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id = mobj.group('id')
-
- page = self._download_webpage(url, video_id)
-
- if re.search(r'>File does not exist<', page) is not None:
- raise ExtractorError('Video %s does not exist' % video_id, expected=True)
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(url, video_id)
- download_form = dict(re.findall(r'<input type="hidden" name="([^"]+)" value="([^"]*)"', page))
+ if '>File does not exist<' in webpage:
+ raise ExtractorError(
+ 'Video %s does not exist' % video_id, expected=True)
- request = compat_urllib_request.Request(url, compat_urllib_parse.urlencode(download_form))
+ download_form = dict(re.findall(
+ r'<input type="hidden" name="([^"]+)" value="([^"]*)"', webpage))
+ request = compat_urllib_request.Request(
+ url, compat_urllib_parse.urlencode(download_form))
request.add_header('Content-Type', 'application/x-www-form-urlencoded')
- video_page = self._download_webpage(request, video_id, 'Downloading video page')
+ video_page = self._download_webpage(
+ request, video_id, 'Downloading video page')
- video_url = self._html_search_regex(r'data-url="([^"]+)"', video_page, 'video URL')
- title = base64.b64decode(self._html_search_meta('full:title', page, 'title')).decode('utf-8')
- filesize = int_or_none(self._html_search_meta('full:size', page, 'file size', fatal=False))
+ video_url = self._html_search_regex(
+ r'data-url="([^"]+)"', video_page, 'video URL')
+ title = base64.b64decode(self._html_search_meta(
+ 'full:title', webpage, 'title')).decode('utf-8')
+ filesize = int_or_none(self._html_search_meta(
+ 'full:size', webpage, 'file size', fatal=False))
thumbnail = self._html_search_regex(
- r'data-poster="([^"]+)"', video_page, 'thumbnail', fatal=False, default=None)
+ r'data-poster="([^"]+)"', video_page, 'thumbnail', default=None)
return {
'id': video_id,