etc/yt-dlp
0
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-23 02:25:11 +00:00
Code Issues Projects Releases Wiki Activity

[vlive:channel] Improve

Browse source
This commit is contained in:
Sergey M․ 2017-01-28 19:08:01 +07:00
parent b92d3c5343
commit 661cc229d2
No known key found for this signature in database
GPG key ID: 2C393E0F18A9236D
1 changed files with 43 additions and 19 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

62
youtube_dl/extractor/vlive.py
View file

@ -6,15 +6,19 @@
import itertools import itertools
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import (
compat_urllib_parse_urlencode,
compat_str,
)
from ..utils import ( from ..utils import (
dict_get, dict_get,
ExtractorError, ExtractorError,
float_or_none, float_or_none,
int_or_none, int_or_none,
remove_start, remove_start,
try_get,
urlencode_postdata, urlencode_postdata,
) )
from ..compat import compat_urllib_parse_urlencode
class VLiveIE(InfoExtractor): class VLiveIE(InfoExtractor):
@ -175,9 +179,9 @@ def _replay(self, video_id, webpage, long_video_id, key):
class VLiveChannelIE(InfoExtractor): class VLiveChannelIE(InfoExtractor):
IE_NAME = 'vlive:channel' IE_NAME = 'vlive:channel'
_VALID_URL = r'https?://channels\.vlive\.tv/(?P<id>[0-9A-Z]+)/video' _VALID_URL = r'https?://channels\.vlive\.tv/(?P<id>[0-9A-Z]+)'
_TEST = { _TEST = {
'url': 'http://channels.vlive.tv/FCD4B/video', 'url': 'http://channels.vlive.tv/FCD4B',
'info_dict': { 'info_dict': {
'id': 'FCD4B', 'id': 'FCD4B',
'title': 'MAMAMOO', 'title': 'MAMAMOO',
@ -191,21 +195,31 @@ def _real_extract(self, url):
webpage = self._download_webpage( webpage = self._download_webpage(
'http://channels.vlive.tv/%s/video' % channel_code, channel_code) 'http://channels.vlive.tv/%s/video' % channel_code, channel_code)
app_id = None
app_js_url = self._search_regex( app_js_url = self._search_regex(
r'(http[^\'\"\s]+app\.js)', webpage, 'app js', default='') r'<script[^>]+src=(["\'])(?P<url>http.+?/app\.js.*?)\1',
webpage, 'app js', default=None, group='url')
if app_js_url: if app_js_url:
app_js = self._download_webpage(app_js_url, channel_code, 'app js') app_js = self._download_webpage(
app_id = self._search_regex( app_js_url, channel_code, 'Downloading app JS', fatal=False)
r'Global\.VFAN_APP_ID\s*=\s*[\'"]([^\'"]+)[\'"]', if app_js:
app_js, 'app id', default=self._APP_ID) app_id = self._search_regex(
else: r'Global\.VFAN_APP_ID\s*=\s*[\'"]([^\'"]+)[\'"]',
app_id = self._APP_ID app_js, 'app id', default=None)
app_id = app_id or self._APP_ID
channel_info = self._download_json( channel_info = self._download_json(
'http://api.vfan.vlive.tv/vproxy/channelplus/decodeChannelCode', 'http://api.vfan.vlive.tv/vproxy/channelplus/decodeChannelCode',
channel_code, note='decode channel code', channel_code, note='Downloading decode channel code',
query={'app_id': app_id, 'channelCode': channel_code, '_': int(time.time())}) query={
'app_id': app_id,
'channelCode': channel_code,
'_': int(time.time())
})
channel_seq = channel_info['result']['channelSeq'] channel_seq = channel_info['result']['channelSeq']
channel_name = None channel_name = None
@ -214,7 +228,7 @@ def _real_extract(self, url):
for page_num in itertools.count(1): for page_num in itertools.count(1):
video_list = self._download_json( video_list = self._download_json(
'http://api.vfan.vlive.tv/vproxy/channelplus/getChannelVideoList', 'http://api.vfan.vlive.tv/vproxy/channelplus/getChannelVideoList',
channel_code, note='channel list %d' % page_num, channel_code, note='Downloading channel list page #%d' % page_num,
query={ query={
'app_id': app_id, 'app_id': app_id,
'channelSeq': channel_seq, 'channelSeq': channel_seq,
@ -223,17 +237,27 @@ def _real_extract(self, url):
'pageNo': page_num 'pageNo': page_num
} }
) )
if not channel_name:
channel_name = video_list['result']['channelInfo']['channelName']
if not video_list['result'].get('videoList'): if not channel_name:
channel_name = try_get(
video_list,
lambda x: x['result']['channelInfo']['channelName'],
compat_str)
videos = try_get(
video_list, lambda x: x['result']['videoList'], list)
if not videos:
break break
for video in video_list['result']['videoList']: for video in videos:
video_id = str(video['videoSeq']) video_id = video.get('videoSeq')
if not video_id:
continue
video_id = compat_str(video_id)
entries.append( entries.append(
self.url_result( self.url_result(
'http://www.vlive.tv/video/%s' % video_id, 'Vlive', video_id)) 'http://www.vlive.tv/video/%s' % video_id,
ie=VLiveIE.ie_key(), video_id=video_id))
return self.playlist_result( return self.playlist_result(
entries, channel_code, channel_name) entries, channel_code, channel_name)