Mirror
/
youtube-dl
mirror of https://github.com/ytdl-org/youtube-dl.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

[xhamster] Futher simplification

pull/2216/head
Philipp Hagemeister 2014-01-23 04:04:35 +01:00
parent 35409e1101
commit 22ff1c4a93
1 changed files with 25 additions and 27 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

52
youtube_dl/extractor/xhamster.py
View File

@ -6,7 +6,6 @@ from .common import InfoExtractor
from ..utils import ( from ..utils import (
compat_urllib_parse, compat_urllib_parse,
unescapeHTML, unescapeHTML,
determine_ext,
ExtractorError, ExtractorError,
) )
@ -16,11 +15,11 @@ class XHamsterIE(InfoExtractor):
_VALID_URL = r'(?:http://)?(?:www\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?' _VALID_URL = r'(?:http://)?(?:www\.)?xhamster\.com/movies/(?P<id>[0-9]+)/(?P<seo>.+?)\.html(?:\?.*)?'
_TESTS = [{ _TESTS = [{
'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html', 'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html',
'file': '1509445.flv', 'file': '1509445.mp4',
'md5': '9f48e0e8d58e3076bb236ff412ab62fa', 'md5': '8281348b8d3c53d39fffb377d24eac4e',
'info_dict': { 'info_dict': {
"upload_date": "20121014", "upload_date": "20121014",
"uploader_id": "Ruseful2011", "uploader_id": "Ruseful2011",
"title": "FemaleAgent Shy beauty takes the bait", "title": "FemaleAgent Shy beauty takes the bait",
"age_limit": 18, "age_limit": 18,
} }
@ -41,7 +40,7 @@ class XHamsterIE(InfoExtractor):
def extract_video_url(webpage): def extract_video_url(webpage):
mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage) mobj = re.search(r'\'srv\': \'(?P<server>[^\']*)\',\s*\'file\': \'(?P<file>[^\']+)\',', webpage)
if mobj is None: if mobj is None:
raise ExtractorError(u'Unable to extract media URL') raise ExtractorError('Unable to extract media URL')
if len(mobj.group('server')) == 0: if len(mobj.group('server')) == 0:
return compat_urllib_parse.unquote(mobj.group('file')) return compat_urllib_parse.unquote(mobj.group('file'))
else: else:
@ -55,7 +54,7 @@ class XHamsterIE(InfoExtractor):
return mp4.group(1) return mp4.group(1)
def is_hd(webpage): def is_hd(webpage):
return webpage.find('<div class=\'icon iconHD\'') != -1 return '<div class=\'icon iconHD\'' in webpage
mobj = re.match(self._VALID_URL, url) mobj = re.match(self._VALID_URL, url)
@ -64,61 +63,60 @@ class XHamsterIE(InfoExtractor):
mrss_url = 'http://xhamster.com/movies/%s/%s.html' % (video_id, seo) mrss_url = 'http://xhamster.com/movies/%s/%s.html' % (video_id, seo)
webpage = self._download_webpage(mrss_url, video_id) webpage = self._download_webpage(mrss_url, video_id)
video_title = self._html_search_regex(r'<title>(?P<title>.+?) - xHamster\.com</title>', video_title = self._html_search_regex(
webpage, 'title') r'<title>(?P<title>.+?) - xHamster\.com</title>', webpage, 'title')
# Only a few videos have an description # Only a few videos have an description
mobj = re.search('<span>Description: </span>(?P<description>[^<]+)', webpage) mobj = re.search(r'<span>Description: </span>([^<]+)', webpage)
if mobj: video_description = mobj.group(1) if mobj else None
video_description = unescapeHTML(mobj.group('description'))
else:
video_description = None
mobj = re.search(r'hint=\'(?P<upload_date_Y>[0-9]{4})-(?P<upload_date_m>[0-9]{2})-(?P<upload_date_d>[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage) mobj = re.search(r'hint=\'(?P<upload_date_Y>[0-9]{4})-(?P<upload_date_m>[0-9]{2})-(?P<upload_date_d>[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage)
if mobj: if mobj:
video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d') video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d')
else: else:
video_upload_date = None video_upload_date = None
self._downloader.report_warning(u'Unable to extract upload date') self._downloader.report_warning('Unable to extract upload date')
video_uploader_id = self._html_search_regex(r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)', video_uploader_id = self._html_search_regex(
webpage, 'uploader id', default=u'anonymous') r'<a href=\'/user/[^>]+>(?P<uploader_id>[^<]+)',
webpage, 'uploader id', default='anonymous')
video_thumbnail = self._search_regex(r'\'image\':\'(?P<thumbnail>[^\']+)\'', video_thumbnail = self._search_regex(
r'\'image\':\'(?P<thumbnail>[^\']+)\'',
webpage, 'thumbnail', fatal=False) webpage, 'thumbnail', fatal=False)
age_limit = self._rta_search(webpage) age_limit = self._rta_search(webpage)
hd = is_hd(webpage) hd = is_hd(webpage)
video_url = extract_video_url(webpage) video_url = extract_video_url(webpage)
formats = [{ formats = [{
'url': video_url, 'url': video_url,
'ext': determine_ext(video_url),
'format': 'hd' if hd else 'sd',
'format_id': 'hd' if hd else 'sd', 'format_id': 'hd' if hd else 'sd',
'preference': 0,
}] }]
video_mp4_url = extract_mp4_video_url(webpage) video_mp4_url = extract_mp4_video_url(webpage)
if (not video_mp4_url is None) and (formats[0]['ext'] != 'mp4'): if video_mp4_url is not None:
formats.append({ formats.append({
'url': video_mp4_url, 'url': video_mp4_url,
'ext': 'mp4', 'ext': 'mp4',
'format': 'hd' if hd else 'sd', 'format_id': 'mp4-hd' if hd else 'mp4-sd',
'format_id': 'hd' if hd else 'sd', 'preference': 1,
}) })
if not hd: if not hd:
webpage = self._download_webpage(mrss_url+'?hd', video_id) 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)
formats.append({ formats.append({
'url': video_url, 'url': video_url,
'ext': determine_ext(video_url),
'format': 'hd',
'format_id': 'hd', 'format_id': 'hd',
'preference': 2,
}) })
self._sort_formats(formats)
return { return {
'id': video_id, 'id': video_id,
'title': video_title, 'title': video_title,