aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor/cliprs.py
diff options
context:
space:
mode:
authorYen Chi Hsuan <yan12125@gmail.com>2016-07-06 20:09:05 +0800
committerYen Chi Hsuan <yan12125@gmail.com>2016-07-06 20:09:05 +0800
commitf8752b86ac66d462caeb44b2ec18eda94973466d (patch)
tree6cdc5c22d3fee54072c425eca34a06052f707194 /youtube_dl/extractor/cliprs.py
parent84c237fb8a2afa06fd3c36f7da9517682e63480e (diff)
[Onet,ClipRs] Add new extractor for onet.tv and use it for clip.rs
Closes #9950
Diffstat (limited to 'youtube_dl/extractor/cliprs.py')
-rw-r--r--youtube_dl/extractor/cliprs.py73
1 files changed, 8 insertions, 65 deletions
diff --git a/youtube_dl/extractor/cliprs.py b/youtube_dl/extractor/cliprs.py
index 4f9320ea5..d55b26d59 100644
--- a/youtube_dl/extractor/cliprs.py
+++ b/youtube_dl/extractor/cliprs.py
@@ -1,16 +1,10 @@
# coding: utf-8
from __future__ import unicode_literals
-from .common import InfoExtractor
-from ..utils import (
- ExtractorError,
- float_or_none,
- int_or_none,
- parse_iso8601,
-)
+from .onet import OnetBaseIE
-class ClipRsIE(InfoExtractor):
+class ClipRsIE(OnetBaseIE):
_VALID_URL = r'https?://(?:www\.)?clip\.rs/(?P<id>[^/]+)/\d+'
_TEST = {
'url': 'http://www.clip.rs/premijera-frajle-predstavljaju-novi-spot-za-pesmu-moli-me-moli/3732',
@@ -27,64 +21,13 @@ class ClipRsIE(InfoExtractor):
}
def _real_extract(self, url):
- video_id = self._match_id(url)
+ display_id = self._match_id(url)
- webpage = self._download_webpage(url, video_id)
+ webpage = self._download_webpage(url, display_id)
- video_id = self._search_regex(
- r'id=(["\'])mvp:(?P<id>.+?)\1', webpage, 'mvp id', group='id')
+ mvp_id = self._search_mvp_id(webpage)
- response = self._download_json(
- 'http://qi.ckm.onetapi.pl/', video_id,
- query={
- 'body[id]': video_id,
- 'body[jsonrpc]': '2.0',
- 'body[method]': 'get_asset_detail',
- 'body[params][ID_Publikacji]': video_id,
- 'body[params][Service]': 'www.onet.pl',
- 'content-type': 'application/jsonp',
- 'x-onet-app': 'player.front.onetapi.pl',
- })
+ info_dict = self._extract_from_id(mvp_id, webpage)
+ info_dict['display_id'] = display_id
- error = response.get('error')
- if error:
- raise ExtractorError(
- '%s said: %s' % (self.IE_NAME, error['message']), expected=True)
-
- video = response['result'].get('0')
-
- formats = []
- for _, formats_dict in video['formats'].items():
- if not isinstance(formats_dict, dict):
- continue
- for format_id, format_list in formats_dict.items():
- if not isinstance(format_list, list):
- continue
- for f in format_list:
- if not f.get('url'):
- continue
- formats.append({
- 'url': f['url'],
- 'format_id': format_id,
- 'height': int_or_none(f.get('vertical_resolution')),
- 'width': int_or_none(f.get('horizontal_resolution')),
- 'abr': float_or_none(f.get('audio_bitrate')),
- 'vbr': float_or_none(f.get('video_bitrate')),
- })
- self._sort_formats(formats)
-
- meta = video.get('meta', {})
-
- title = self._og_search_title(webpage, default=None) or meta['title']
- description = self._og_search_description(webpage, default=None) or meta.get('description')
- duration = meta.get('length') or meta.get('lenght')
- timestamp = parse_iso8601(meta.get('addDate'), ' ')
-
- return {
- 'id': video_id,
- 'title': title,
- 'description': description,
- 'duration': duration,
- 'timestamp': timestamp,
- 'formats': formats,
- }
+ return info_dict