w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[gamespot] Modernize

Browse source
This commit is contained in:
Philipp Hagemeister 2014-11-04 23:04:12 +01:00
parent 94bd361318
commit a32f253112
1 changed files with 8 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

14
youtube_dl/extractor/gamespot.py
View file

@ -13,7 +13,7 @@ from ..utils import (
class GameSpotIE(InfoExtractor): class GameSpotIE(InfoExtractor):
_VALID_URL = r'(?:http://)?(?:www\.)?gamespot\.com/.*-(?P<page_id>\d+)/?' _VALID_URL = r'(?:http://)?(?:www\.)?gamespot\.com/.*-(?P<id>\d+)/?'
_TEST = { _TEST = {
'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/', 'url': 'http://www.gamespot.com/videos/arma-3-community-guide-sitrep-i/2300-6410818/',
'md5': 'b2a30deaa8654fcccd43713a6b6a4825', 'md5': 'b2a30deaa8654fcccd43713a6b6a4825',
@ -26,10 +26,10 @@ class GameSpotIE(InfoExtractor):
} }
def _real_extract(self, url): def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url) page_id = self._match_id(url)
page_id = mobj.group('page_id')
webpage = self._download_webpage(url, page_id) webpage = self._download_webpage(url, page_id)
data_video_json = self._search_regex(r'data-video=["\'](.*?)["\']', webpage, 'data video') data_video_json = self._search_regex(
r'data-video=["\'](.*?)["\']', webpage, 'data video')
data_video = json.loads(unescapeHTML(data_video_json)) data_video = json.loads(unescapeHTML(data_video_json))
# Transform the manifest url to a link to the mp4 files # Transform the manifest url to a link to the mp4 files
@ -41,7 +41,8 @@ class GameSpotIE(InfoExtractor):
http_path = f4m_path[1:].split('/', 1)[1] http_path = f4m_path[1:].split('/', 1)[1]
http_template = re.sub(QUALITIES_RE, r'%s', http_path) http_template = re.sub(QUALITIES_RE, r'%s', http_path)
http_template = http_template.replace('.csmil/manifest.f4m', '') http_template = http_template.replace('.csmil/manifest.f4m', '')
http_template = compat_urlparse.urljoin('http://video.gamespotcdn.com/', http_template) http_template = compat_urlparse.urljoin(
'http://video.gamespotcdn.com/', http_template)
formats = [] formats = []
for q in qualities: for q in qualities:
formats.append({ formats.append({
@ -52,8 +53,9 @@ class GameSpotIE(InfoExtractor):
return { return {
'id': data_video['guid'], 'id': data_video['guid'],
'display_id': page_id,
'title': compat_urllib_parse.unquote(data_video['title']), 'title': compat_urllib_parse.unquote(data_video['title']),
'formats': formats, 'formats': formats,
'description': get_meta_content('description', webpage), 'description': self._html_search_meta('description', webpage),
'thumbnail': self._og_search_thumbnail(webpage), 'thumbnail': self._og_search_thumbnail(webpage),
} }