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

[bilibili] use xpath_text and catch errors in xml document

Browse source
This commit is contained in:
remitamine 2015-12-03 22:01:32 +01:00
parent 24dc1ed715
commit 76ab842d9b
1 changed files with 11 additions and 14 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

25
youtube_dl/extractor/bilibili.py
View file

@ -7,11 +7,13 @@
from .common import InfoExtractor from .common import InfoExtractor
from ..compat import ( from ..compat import (
compat_etree_fromstring, compat_etree_fromstring,
compat_str,
) )
from ..utils import ( from ..utils import (
int_or_none, int_or_none,
unescapeHTML, unescapeHTML,
ExtractorError, ExtractorError,
xpath_text,
) )
@ -58,27 +60,22 @@ def _real_extract(self, url):
cid = view_data['cid'] cid = view_data['cid']
title = unescapeHTML(view_data['title']) title = unescapeHTML(view_data['title'])
page = self._download_webpage( doc = self._download_xml(
'http://interface.bilibili.com/v_cdn_play?appkey=8e9fc618fbd41e28&cid=%s' % cid, 'http://interface.bilibili.com/v_cdn_play?appkey=8e9fc618fbd41e28&cid=%s' % cid,
cid, cid,
'Downloading page %s/%s' % (page_num, view_data['pages']) 'Downloading page %s/%s' % (page_num, view_data['pages'])
) )
try:
err_info = json.loads(page)
raise ExtractorError(
'BiliBili said: ' + err_info['error_text'], expected=True)
except ValueError:
pass
doc = compat_etree_fromstring(page) if xpath_text(doc, './result') == 'error':
raise ExtractorError('%s said: %s' % (self.IE_NAME, xpath_text(doc, './message')), expected=True)
entries = [] entries = []
for durl in doc.findall('./durl'): for durl in doc.findall('./durl'):
size = durl.find('./filesize|./size') size = xpath_text(durl, ['./filesize', './size'])
formats = [{ formats = [{
'url': durl.find('./url').text, 'url': durl.find('./url').text,
'filesize': int_or_none(size.text) if size else None, 'filesize': int_or_none(size),
'ext': 'flv', 'ext': 'flv',
}] }]
backup_urls = durl.find('./backup_url') backup_urls = durl.find('./backup_url')
@ -88,21 +85,21 @@ def _real_extract(self, url):
formats.reverse() formats.reverse()
entries.append({ entries.append({
'id': '%s_part%s' % (cid, durl.find('./order').text), 'id': '%s_part%s' % (cid, xpath_text(durl, './order')),
'title': title, 'title': title,
'duration': int_or_none(durl.find('./length').text) // 1000, 'duration': int_or_none(xpath_text(durl, './length'), 1000),
'formats': formats, 'formats': formats,
}) })
info = { info = {
'id': str(cid), 'id': compat_str(cid),
'title': title, 'title': title,
'description': view_data.get('description'), 'description': view_data.get('description'),
'thumbnail': view_data.get('pic'), 'thumbnail': view_data.get('pic'),
'uploader': view_data.get('author'), 'uploader': view_data.get('author'),
'timestamp': int_or_none(view_data.get('created')), 'timestamp': int_or_none(view_data.get('created')),
'view_count': view_data.get('play'), 'view_count': view_data.get('play'),
'duration': int_or_none(doc.find('./timelength').text), 'duration': int_or_none(xpath_text(doc, './timelength')),
} }
if len(entries) == 1: if len(entries) == 1: