github-com-ytdl-org/youtube-dl
1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-01-07 17:16:08 +00:00
Code Issues Releases Wiki Activity

[ard] Make more robust against missing thumbnails

Browse source 
I cannot reproduce this error, it's from travis.
This commit is contained in:
Philipp Hagemeister 2014-09-13 09:09:55 +02:00
parent dc752ff442
commit bf0ff93277
2 changed files with 15 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

6
youtube_dl/extractor/ard.py
View file

@ -13,6 +13,7 @@ from ..utils import (
int_or_none, int_or_none,
parse_duration, parse_duration,
unified_strdate, unified_strdate,
xpath_text,
) )
@ -157,8 +158,9 @@ class ARDIE(InfoExtractor):
player_url = mobj.group('mainurl') + '~playerXml.xml' player_url = mobj.group('mainurl') + '~playerXml.xml'
doc = self._download_xml(player_url, display_id) doc = self._download_xml(player_url, display_id)
video_node = doc.find('./video') video_node = doc.find('./video')
upload_date = unified_strdate(video_node.find('./broadcastDate').text) upload_date = unified_strdate(xpath_text(
thumbnail = video_node.find('.//teaserImage//variant/url').text video_node, './broadcastDate'))
thumbnail = xpath_text(video_node, './/teaserImage//variant/url')
formats = [] formats = []
for a in video_node.findall('.//asset'): for a in video_node.findall('.//asset'):

11
youtube_dl/utils.py
View file

@ -304,6 +304,17 @@ def xpath_with_ns(path, ns_map):
return '/'.join(replaced) return '/'.join(replaced)
def xpath_text(node, xpath, name=None, fatal=False):
n = node.find(xpath)
if n is None:
if fatal:
name = xpath if name is None else name
raise ExtractorError('Could not find XML element %s' % name)
else:
return None
return n.text
compat_html_parser.locatestarttagend = re.compile(r"""<[a-zA-Z][-.a-zA-Z0-9:_]*(?:\s+(?:(?<=['"\s])[^\s/>][^\s/=>]*(?:\s*=+\s*(?:'[^']*'|"[^"]*"|(?!['"])[^>\s]*))?\s*)*)?\s*""", re.VERBOSE) # backport bugfix compat_html_parser.locatestarttagend = re.compile(r"""<[a-zA-Z][-.a-zA-Z0-9:_]*(?:\s+(?:(?<=['"\s])[^\s/>][^\s/=>]*(?:\s*=+\s*(?:'[^']*'|"[^"]*"|(?!['"])[^>\s]*))?\s*)*)?\s*""", re.VERBOSE) # backport bugfix
class BaseHTMLParser(compat_html_parser.HTMLParser): class BaseHTMLParser(compat_html_parser.HTMLParser):
def __init(self): def __init(self):