xZero707/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-27 14:15:37 +01:00
Code Issues Packages Projects Releases Wiki Activity

[xhamster] Make more robust

Browse Source
This commit is contained in:
Sergey M․ 2015-08-05 20:32:44 +06:00
parent defce60385
commit be7a8379b4
1 changed files with 10 additions and 8 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

18
youtube_dl/extractor/xhamster.py
View File

@ -46,12 +46,12 @@ class XHamsterIE(InfoExtractor):
] ]
def _real_extract(self, url): def _real_extract(self, url):
def extract_video_url(webpage): def extract_video_url(webpage, name):
mp4 = re.search(r'file:\s+\'([^\']+)\'', webpage) return self._search_regex(
if mp4 is None: [r'''file\s*:\s*(?P<q>["'])(?P<mp4>.+?)(?P=q)''',
raise ExtractorError('Unable to extract media URL') r'''<a\s+href=(?P<q>["'])(?P<mp4>.+?)(?P=q)\s+class=["']mp4Thumb''',
else: r'''<video[^>]+file=(?P<q>["'])(?P<mp4>.+?)(?P=q)[^>]*>'''],
return mp4.group(1) webpage, name, group='mp4')
def is_hd(webpage): def is_hd(webpage):
return '<div class=\'icon iconHD\'' in webpage return '<div class=\'icon iconHD\'' in webpage
@ -97,7 +97,9 @@ class XHamsterIE(InfoExtractor):
hd = is_hd(webpage) hd = is_hd(webpage)
video_url = extract_video_url(webpage) format_id = 'hd' if hd else 'sd'
video_url = extract_video_url(webpage, format_id)
formats = [{ formats = [{
'url': video_url, 'url': video_url,
'format_id': 'hd' if hd else 'sd', 'format_id': 'hd' if hd else 'sd',
@ -108,7 +110,7 @@ class XHamsterIE(InfoExtractor):
mrss_url = self._search_regex(r'<link rel="canonical" href="([^"]+)', webpage, 'mrss_url') mrss_url = self._search_regex(r'<link rel="canonical" href="([^"]+)', webpage, 'mrss_url')
webpage = self._download_webpage(mrss_url + '?hd', video_id, note='Downloading HD webpage') webpage = self._download_webpage(mrss_url + '?hd', video_id, note='Downloading HD webpage')
if is_hd(webpage): if is_hd(webpage):
video_url = extract_video_url(webpage) video_url = extract_video_url(webpage, 'hd')
formats.append({ formats.append({
'url': video_url, 'url': video_url,
'format_id': 'hd', 'format_id': 'hd',