github/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-11-21 20:46:36 -05:00
Code Issues Projects Releases Packages Wiki Activity

[brightcove] Handle non well-formed XMLs (#5421)

Browse source
This commit is contained in:
Sergey M․ 2015-04-14 17:50:53 +06:00
parent 476e1095fa
commit 94c1255782
1 changed files with 5 additions and 2 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
youtube_dl/extractor/brightcove.py
View file

@ -117,7 +117,10 @@ def _build_brighcove_url(cls, object_str):
object_str = re.sub(r'(<object[^>]*)(xmlns=".*?")', r'\1', object_str)
object_str = fix_xml_ampersands(object_str)
object_doc = xml.etree.ElementTree.fromstring(object_str.encode('utf-8'))
try:
object_doc = xml.etree.ElementTree.fromstring(object_str.encode('utf-8'))
except xml.etree.ElementTree.ParseError:
return
fv_el = find_xpath_attr(object_doc, './param', 'name', 'flashVars')
if fv_el is not None:
@ -185,7 +188,7 @@ def _extract_brightcove_urls(cls, webpage):
[^>]*?>\s*<param\s+name="movie"\s+value="https?://[^/]*brightcove\.com/
).+?>\s*</object>''',
webpage)
return [cls._build_brighcove_url(m) for m in matches]
return filter(None, [cls._build_brighcove_url(m) for m in matches])
def _real_extract(self, url):
url, smuggled_data = unsmuggle_url(url, {})