[kwuo] Fix KuwoChartIE and KuwoSingerIE and accept new URL forms

This commit is contained in:
Yen Chi Hsuan 2016-03-20 20:17:56 +08:00
parent 7caae128a7
commit daef04a4e7

View File

@ -2,13 +2,13 @@
from __future__ import unicode_literals from __future__ import unicode_literals
import re import re
import itertools
from .common import InfoExtractor from .common import InfoExtractor
from ..utils import ( from ..utils import (
get_element_by_id, get_element_by_id,
clean_html, clean_html,
ExtractorError, ExtractorError,
InAdvancePagedList,
remove_start, remove_start,
) )
@ -55,7 +55,7 @@ def _get_formats(self, song_id, tolerate_ip_deny=False):
class KuwoIE(KuwoBaseIE): class KuwoIE(KuwoBaseIE):
IE_NAME = 'kuwo:song' IE_NAME = 'kuwo:song'
IE_DESC = '酷我音乐' IE_DESC = '酷我音乐'
_VALID_URL = r'http://www\.kuwo\.cn/yinyue/(?P<id>\d+?)/' _VALID_URL = r'http://www\.kuwo\.cn/yinyue/(?P<id>\d+?)'
_TESTS = [{ _TESTS = [{
'url': 'http://www.kuwo.cn/yinyue/635632/', 'url': 'http://www.kuwo.cn/yinyue/635632/',
'info_dict': { 'info_dict': {
@ -80,6 +80,9 @@ class KuwoIE(KuwoBaseIE):
'params': { 'params': {
'format': 'mp3-320' 'format': 'mp3-320'
}, },
}, {
'url': 'http://www.kuwo.cn/yinyue/3197154?catalog=yueku2016',
'only_matching': True,
}] }]
def _real_extract(self, url): def _real_extract(self, url):
@ -172,8 +175,6 @@ class KuwoChartIE(InfoExtractor):
'url': 'http://yinyue.kuwo.cn/billboard_香港中文龙虎榜.htm', 'url': 'http://yinyue.kuwo.cn/billboard_香港中文龙虎榜.htm',
'info_dict': { 'info_dict': {
'id': '香港中文龙虎榜', 'id': '香港中文龙虎榜',
'title': '香港中文龙虎榜',
'description': 're:\d{4}\d{2}',
}, },
'playlist_mincount': 10, 'playlist_mincount': 10,
} }
@ -184,17 +185,11 @@ def _real_extract(self, url):
url, chart_id, note='Download chart info', url, chart_id, note='Download chart info',
errnote='Unable to get chart info') errnote='Unable to get chart info')
chart_name = self._html_search_regex(
r'<h1[^>]+class="unDis">([^<]+)</h1>', webpage, 'chart name')
chart_desc = self._html_search_regex(
r'<p[^>]+class="tabDef">(\d{4}\d{2}期)</p>', webpage, 'chart desc')
entries = [ entries = [
self.url_result(song_url, 'Kuwo') for song_url in re.findall( self.url_result(song_url, 'Kuwo') for song_url in re.findall(
r'<a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)/"', webpage) r'<a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)', webpage)
] ]
return self.playlist_result(entries, chart_id, chart_name, chart_desc) return self.playlist_result(entries, chart_id)
class KuwoSingerIE(InfoExtractor): class KuwoSingerIE(InfoExtractor):
@ -207,7 +202,7 @@ class KuwoSingerIE(InfoExtractor):
'id': 'bruno+mars', 'id': 'bruno+mars',
'title': 'Bruno Mars', 'title': 'Bruno Mars',
}, },
'playlist_count': 10, 'playlist_mincount': 329,
}, { }, {
'url': 'http://www.kuwo.cn/mingxing/Ali/music.htm', 'url': 'http://www.kuwo.cn/mingxing/Ali/music.htm',
'info_dict': { 'info_dict': {
@ -218,6 +213,8 @@ class KuwoSingerIE(InfoExtractor):
'skip': 'Regularly stalls travis build', # See https://travis-ci.org/rg3/youtube-dl/jobs/78878540 'skip': 'Regularly stalls travis build', # See https://travis-ci.org/rg3/youtube-dl/jobs/78878540
}] }]
PAGE_SIZE = 15
def _real_extract(self, url): def _real_extract(self, url):
singer_id = self._match_id(url) singer_id = self._match_id(url)
webpage = self._download_webpage( webpage = self._download_webpage(
@ -225,25 +222,28 @@ def _real_extract(self, url):
errnote='Unable to get singer info') errnote='Unable to get singer info')
singer_name = self._html_search_regex( singer_name = self._html_search_regex(
r'<div class="title clearfix">\s*<h1>([^<]+)<span', webpage, 'singer name' r'<h1>([^<]+)</h1>', webpage, 'singer name')
)
entries = [] artist_id = self._html_search_regex(
first_page_only = False if re.search(r'/music(?:_\d+)?\.htm', url) else True r'data-artistid="(\d+)"', webpage, 'artist id')
for page_num in itertools.count(1):
page_count = int(self._html_search_regex(
r'data-page="(\d+)"', webpage, 'page count'))
def page_func(page_num):
webpage = self._download_webpage( webpage = self._download_webpage(
'http://www.kuwo.cn/mingxing/%s/music_%d.htm' % (singer_id, page_num), 'http://www.kuwo.cn/artist/contentMusicsAjax',
singer_id, note='Download song list page #%d' % page_num, singer_id, note='Download song list page #%d' % (page_num + 1),
errnote='Unable to get song list page #%d' % page_num) errnote='Unable to get song list page #%d' % (page_num + 1),
query={'artistId': artist_id, 'pn': page_num, 'rn': self.PAGE_SIZE})
entries.extend([ return [
self.url_result(song_url, 'Kuwo') for song_url in re.findall( self.url_result(song_url, 'Kuwo') for song_url in re.findall(
r'<p[^>]+class="m_name"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)/', r'<div[^>]+class="name"><a[^>]+href="(http://www\.kuwo\.cn/yinyue/\d+)',
webpage) webpage)
][:10 if first_page_only else None]) ]
if first_page_only or not re.search(r'<a[^>]+href="[^"]+">下一页</a>', webpage): entries = InAdvancePagedList(page_func, page_count, self.PAGE_SIZE)
break
return self.playlist_result(entries, singer_id, singer_name) return self.playlist_result(entries, singer_id, singer_name)