pepepper/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl synced 2024-12-22 20:20:09 +09:00
Code Issues Projects Releases Wiki Activity

[rottentomatoes] Fix extraction

Browse Source 
Closes #10467
This commit is contained in:
Yen Chi Hsuan 2016-09-04 16:25:59 +08:00
parent 37c7490ac6
commit 622638512b
No known key found for this signature in database
GPG Key ID: 3FDDD575826C5C30
2 changed files with 23 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
ChangeLog
View File

@ -1,6 +1,7 @@
version <unreleased> version <unreleased>
Extractors Extractors
* [rottentomatoes] Fix extraction (#10467)
* [youjizz] Fix extraction (#10437) * [youjizz] Fix extraction (#10437)
+ [foxnews] Add support for FoxNews Insider (#10445) + [foxnews] Add support for FoxNews Insider (#10445)
+ [fc2] Recognize Flash player URLs (#10512) + [fc2] Recognize Flash player URLs (#10512)

30
youtube_dl/extractor/rottentomatoes.py
View File

@ -1,8 +1,7 @@
from __future__ import unicode_literals from __future__ import unicode_literals
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import compat_urlparse from ..utils import js_to_json
from .internetvideoarchive import InternetVideoArchiveIE
class RottenTomatoesIE(InfoExtractor): class RottenTomatoesIE(InfoExtractor):
@ -11,21 +10,36 @@ class RottenTomatoesIE(InfoExtractor):
_TEST = { _TEST = {
'url': 'http://www.rottentomatoes.com/m/toy_story_3/trailers/11028566/', 'url': 'http://www.rottentomatoes.com/m/toy_story_3/trailers/11028566/',
'info_dict': { 'info_dict': {
'id': '613340', 'id': '11028566',
'ext': 'mp4', 'ext': 'mp4',
'title': 'Toy Story 3', 'title': 'Toy Story 3',
'thumbnail': 're:^https?://.*\.jpg$',
}, },
} }
def _real_extract(self, url): def _real_extract(self, url):
video_id = self._match_id(url) video_id = self._match_id(url)
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
og_video = self._og_search_video_url(webpage)
query = compat_urlparse.urlparse(og_video).query params = self._parse_json(
self._search_regex(r'(?s)RTVideo\(({.+?})\);', webpage, 'player parameters'),
video_id, transform_source=lambda s: js_to_json(s.replace('window.location.href', '""')))
formats = []
if params.get('urlHLS'):
formats.extend(self._extract_m3u8_formats(
params['urlHLS'], video_id, ext='mp4',
entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
if params.get('urlMP4'):
formats.append({
'url': params['urlMP4'],
'format_id': 'mp4',
})
self._sort_formats(formats)
return { return {
'_type': 'url_transparent', 'id': video_id,
'url': InternetVideoArchiveIE._build_xml_url(query),
'ie_key': InternetVideoArchiveIE.ie_key(),
'title': self._og_search_title(webpage), 'title': self._og_search_title(webpage),
'formats': formats,
'thumbnail': params.get('thumbnailImg'),
} }