diff options
| -rw-r--r-- | youtube_dl/extractor/common.py | 2 | ||||
| -rw-r--r-- | youtube_dl/extractor/jpopsukitv.py | 68 |
2 files changed, 39 insertions, 31 deletions
diff --git a/youtube_dl/extractor/common.py b/youtube_dl/extractor/common.py index f7247752e..f498bcf6f 100644 --- a/youtube_dl/extractor/common.py +++ b/youtube_dl/extractor/common.py @@ -378,7 +378,7 @@ class InfoExtractor(object): @staticmethod def _og_regexes(prop): content_re = r'content=(?:"([^>]+?)"|\'(.+?)\')' - property_re = r'property=[\'"]og:%s[\'"]' % re.escape(prop) + property_re = r'(?:name|property)=[\'"]og:%s[\'"]' % re.escape(prop) template = r'<meta[^>]+?%s[^>]+?%s' return [ template % (property_re, content_re), diff --git a/youtube_dl/extractor/jpopsukitv.py b/youtube_dl/extractor/jpopsukitv.py index 5e8f91d51..aad782578 100644 --- a/youtube_dl/extractor/jpopsukitv.py +++ b/youtube_dl/extractor/jpopsukitv.py @@ -1,25 +1,31 @@ # coding=utf-8 +from __future__ import unicode_literals + import re -from ..utils import unified_strdate + from .common import InfoExtractor +from ..utils import ( + int_or_none, + unified_strdate, +) class JpopsukiIE(InfoExtractor): - IE_NAME = u'jpopsuki.tv' + IE_NAME = 'jpopsuki.tv' _VALID_URL = r'https?://(?:www\.)?jpopsuki\.tv/video/(.*?)/(?P<id>\S+)' _TEST = { - u'url': u'http://www.jpopsuki.tv/video/ayumi-hamasaki---evolution/00be659d23b0b40508169cdee4545771', - u'md5': u'88018c0c1a9b1387940e90ec9e7e198e', - u'file': u'00be659d23b0b40508169cdee4545771.mp4', - u'info_dict': { - u'id': u'00be659d23b0b40508169cdee4545771', - u'title': u'ayumi hamasaki - evolution', - 'description': u'Release date: 2001.01.31\r 浜崎あゆみ - evolution', - 'thumbnail': u'http://www.jpopsuki.tv/cache/89722c74d2a2ebe58bcac65321c115b2.jpg', - 'uploader': u'plama_chan', - 'uploader_id': u'404', - 'upload_date': u'20121101' + 'url': 'http://www.jpopsuki.tv/video/ayumi-hamasaki---evolution/00be659d23b0b40508169cdee4545771', + 'md5': '88018c0c1a9b1387940e90ec9e7e198e', + 'file': '00be659d23b0b40508169cdee4545771.mp4', + 'info_dict': { + 'id': '00be659d23b0b40508169cdee4545771', + 'title': 'ayumi hamasaki - evolution', + 'description': 'Release date: 2001.01.31\r\n浜崎あゆみ - evolution', + 'thumbnail': 'http://www.jpopsuki.tv/cache/89722c74d2a2ebe58bcac65321c115b2.jpg', + 'uploader': 'plama_chan', + 'uploader_id': '404', + 'upload_date': '20121101' } } @@ -30,26 +36,28 @@ class JpopsukiIE(InfoExtractor): webpage = self._download_webpage(url, video_id) video_url = 'http://www.jpopsuki.tv' + self._html_search_regex( - r'<source src="(.*?)" type', webpage, u'video url') + r'<source src="(.*?)" type', webpage, 'video url') - video_title = self._html_search_regex( - r'<meta name="og:title" content="(.*?)" />', webpage, u'video title') - description = self._html_search_regex( - r'<meta name="og:description" content="(.*?)" />', webpage, u'video description', flags=re.DOTALL) - thumbnail = self._html_search_regex( - r'<meta name="og:image" content="(.*?)" />', webpage, u'video thumbnail') + video_title = self._og_search_title(webpage) + description = self._og_search_description(webpage) + thumbnail = self._og_search_thumbnail(webpage) uploader = self._html_search_regex( - r'<li>from: <a href="/user/view/user/(.*?)/uid/', webpage, u'video uploader') + r'<li>from: <a href="/user/view/user/(.*?)/uid/', + webpage, 'video uploader', fatal=False) uploader_id = self._html_search_regex( - r'<li>from: <a href="/user/view/user/\S*?/uid/(\d*)', webpage, u'video uploader_id') + r'<li>from: <a href="/user/view/user/\S*?/uid/(\d*)', + webpage, 'video uploader_id', fatal=False) upload_date = self._html_search_regex( - r'<li>uploaded: (.*?)</li>', webpage, u'video upload_date') + r'<li>uploaded: (.*?)</li>', webpage, 'video upload_date', + fatal=False) if upload_date is not None: upload_date = unified_strdate(upload_date) - view_count = self._html_search_regex( - r'<li>Hits: (\d*?)</li>', webpage, u'video view_count') - comment_count = self._html_search_regex( - r'<h2>(\d*?) comments</h2>', webpage, u'video comment_count') + view_count_str = self._html_search_regex( + r'<li>Hits: ([0-9]+?)</li>', webpage, 'video view_count', + fatal=False) + comment_count_str = self._html_search_regex( + r'<h2>([0-9]+?) comments</h2>', webpage, 'video comment_count', + fatal=False) return { 'id': video_id, @@ -60,6 +68,6 @@ class JpopsukiIE(InfoExtractor): 'uploader': uploader, 'uploader_id': uploader_id, 'upload_date': upload_date, - 'view_count': view_count, - 'comment_count': comment_count, - }
\ No newline at end of file + 'view_count': int_or_none(view_count_str), + 'comment_count': int_or_none(comment_count_str), + } |