From 22ff1c4a9374b45359db5d9bab6abf26aaaf0f73 Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Thu, 23 Jan 2014 04:04:35 +0100 Subject: [PATCH] [xhamster] Futher simplification --- youtube_dl/extractor/xhamster.py | 52 +++++++++++++++----------------- 1 file changed, 25 insertions(+), 27 deletions(-) diff --git a/youtube_dl/extractor/xhamster.py b/youtube_dl/extractor/xhamster.py index 833d2d1b4..d317f29f2 100644 --- a/youtube_dl/extractor/xhamster.py +++ b/youtube_dl/extractor/xhamster.py @@ -6,7 +6,6 @@ from .common import InfoExtractor from ..utils import ( compat_urllib_parse, unescapeHTML, - determine_ext, ExtractorError, ) @@ -16,11 +15,11 @@ class XHamsterIE(InfoExtractor): _VALID_URL = r'(?:http://)?(?:www\.)?xhamster\.com/movies/(?P[0-9]+)/(?P.+?)\.html(?:\?.*)?' _TESTS = [{ 'url': 'http://xhamster.com/movies/1509445/femaleagent_shy_beauty_takes_the_bait.html', - 'file': '1509445.flv', - 'md5': '9f48e0e8d58e3076bb236ff412ab62fa', + 'file': '1509445.mp4', + 'md5': '8281348b8d3c53d39fffb377d24eac4e', 'info_dict': { - "upload_date": "20121014", - "uploader_id": "Ruseful2011", + "upload_date": "20121014", + "uploader_id": "Ruseful2011", "title": "FemaleAgent Shy beauty takes the bait", "age_limit": 18, } @@ -41,7 +40,7 @@ class XHamsterIE(InfoExtractor): def extract_video_url(webpage): mobj = re.search(r'\'srv\': \'(?P[^\']*)\',\s*\'file\': \'(?P[^\']+)\',', webpage) 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: return compat_urllib_parse.unquote(mobj.group('file')) else: @@ -55,7 +54,7 @@ class XHamsterIE(InfoExtractor): return mp4.group(1) def is_hd(webpage): - return webpage.find('
(?P.+?) - xHamster\.com', - webpage, 'title') + video_title = self._html_search_regex( + r'(?P<title>.+?) - xHamster\.com', webpage, 'title') # Only a few videos have an description - mobj = re.search('Description: (?P[^<]+)', webpage) - if mobj: - video_description = unescapeHTML(mobj.group('description')) - else: - video_description = None + mobj = re.search(r'Description: ([^<]+)', webpage) + video_description = mobj.group(1) if mobj else None mobj = re.search(r'hint=\'(?P[0-9]{4})-(?P[0-9]{2})-(?P[0-9]{2}) [0-9]{2}:[0-9]{2}:[0-9]{2} [A-Z]{3,4}\'', webpage) if mobj: video_upload_date = mobj.group('upload_date_Y')+mobj.group('upload_date_m')+mobj.group('upload_date_d') else: 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']+>(?P[^<]+)', - webpage, 'uploader id', default=u'anonymous') + video_uploader_id = self._html_search_regex( + r']+>(?P[^<]+)', + webpage, 'uploader id', default='anonymous') - video_thumbnail = self._search_regex(r'\'image\':\'(?P[^\']+)\'', + video_thumbnail = self._search_regex( + r'\'image\':\'(?P[^\']+)\'', webpage, 'thumbnail', fatal=False) age_limit = self._rta_search(webpage) hd = is_hd(webpage) - video_url = extract_video_url(webpage) formats = [{ 'url': video_url, - 'ext': determine_ext(video_url), - 'format': 'hd' if hd else 'sd', 'format_id': 'hd' if hd else 'sd', + 'preference': 0, }] 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({ 'url': video_mp4_url, 'ext': 'mp4', - 'format': 'hd' if hd else 'sd', - 'format_id': 'hd' if hd else 'sd', + 'format_id': 'mp4-hd' if hd else 'mp4-sd', + 'preference': 1, }) 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): video_url = extract_video_url(webpage) formats.append({ 'url': video_url, - 'ext': determine_ext(video_url), - 'format': 'hd', 'format_id': 'hd', + 'preference': 2, }) + self._sort_formats(formats) + return { 'id': video_id, 'title': video_title,