[jpopsuki] Simplify

This commit is contained in:
Philipp Hagemeister 2014-01-03 12:51:37 +01:00
parent d2fee313ec
commit 9887c9b2d6
2 changed files with 39 additions and 31 deletions

View file

@ -378,7 +378,7 @@ class InfoExtractor(object):
@staticmethod @staticmethod
def _og_regexes(prop): def _og_regexes(prop):
content_re = r'content=(?:"([^>]+?)"|\'(.+?)\')' 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' template = r'<meta[^>]+?%s[^>]+?%s'
return [ return [
template % (property_re, content_re), template % (property_re, content_re),

View file

@ -1,25 +1,31 @@
# coding=utf-8 # coding=utf-8
from __future__ import unicode_literals
import re import re
from ..utils import unified_strdate
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import (
int_or_none,
unified_strdate,
)
class JpopsukiIE(InfoExtractor): class JpopsukiIE(InfoExtractor):
IE_NAME = u'jpopsuki.tv' IE_NAME = 'jpopsuki.tv'
_VALID_URL = r'https?://(?:www\.)?jpopsuki\.tv/video/(.*?)/(?P<id>\S+)' _VALID_URL = r'https?://(?:www\.)?jpopsuki\.tv/video/(.*?)/(?P<id>\S+)'
_TEST = { _TEST = {
u'url': u'http://www.jpopsuki.tv/video/ayumi-hamasaki---evolution/00be659d23b0b40508169cdee4545771', 'url': 'http://www.jpopsuki.tv/video/ayumi-hamasaki---evolution/00be659d23b0b40508169cdee4545771',
u'md5': u'88018c0c1a9b1387940e90ec9e7e198e', 'md5': '88018c0c1a9b1387940e90ec9e7e198e',
u'file': u'00be659d23b0b40508169cdee4545771.mp4', 'file': '00be659d23b0b40508169cdee4545771.mp4',
u'info_dict': { 'info_dict': {
u'id': u'00be659d23b0b40508169cdee4545771', 'id': '00be659d23b0b40508169cdee4545771',
u'title': u'ayumi hamasaki - evolution', 'title': 'ayumi hamasaki - evolution',
'description': u'Release date: 2001.01.31\r 浜崎あゆみ - evolution', 'description': 'Release date: 2001.01.31\r\n浜崎あゆみ - evolution',
'thumbnail': u'http://www.jpopsuki.tv/cache/89722c74d2a2ebe58bcac65321c115b2.jpg', 'thumbnail': 'http://www.jpopsuki.tv/cache/89722c74d2a2ebe58bcac65321c115b2.jpg',
'uploader': u'plama_chan', 'uploader': 'plama_chan',
'uploader_id': u'404', 'uploader_id': '404',
'upload_date': u'20121101' 'upload_date': '20121101'
} }
} }
@ -30,26 +36,28 @@ class JpopsukiIE(InfoExtractor):
webpage = self._download_webpage(url, video_id) webpage = self._download_webpage(url, video_id)
video_url = 'http://www.jpopsuki.tv' + self._html_search_regex( 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( video_title = self._og_search_title(webpage)
r'<meta name="og:title" content="(.*?)" />', webpage, u'video title') description = self._og_search_description(webpage)
description = self._html_search_regex( thumbnail = self._og_search_thumbnail(webpage)
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')
uploader = self._html_search_regex( 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( 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( 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: if upload_date is not None:
upload_date = unified_strdate(upload_date) upload_date = unified_strdate(upload_date)
view_count = self._html_search_regex( view_count_str = self._html_search_regex(
r'<li>Hits: (\d*?)</li>', webpage, u'video view_count') r'<li>Hits: ([0-9]+?)</li>', webpage, 'video view_count',
comment_count = self._html_search_regex( fatal=False)
r'<h2>(\d*?) comments</h2>', webpage, u'video comment_count') comment_count_str = self._html_search_regex(
r'<h2>([0-9]+?) comments</h2>', webpage, 'video comment_count',
fatal=False)
return { return {
'id': video_id, 'id': video_id,
@ -60,6 +68,6 @@ class JpopsukiIE(InfoExtractor):
'uploader': uploader, 'uploader': uploader,
'uploader_id': uploader_id, 'uploader_id': uploader_id,
'upload_date': upload_date, 'upload_date': upload_date,
'view_count': view_count, 'view_count': int_or_none(view_count_str),
'comment_count': comment_count, 'comment_count': int_or_none(comment_count_str),
} }