mirror of
https://github.com/yt-dlp/yt-dlp.git
synced 2024-09-06 02:49:35 +02:00
some HTMLParser bugfixes
This commit is contained in:
parent
9e6dd23876
commit
9beb5af82e
BIN
youtube-dl
BIN
youtube-dl
Binary file not shown.
BIN
youtube-dl.exe
BIN
youtube-dl.exe
Binary file not shown.
@ -359,8 +359,8 @@ def _real_extract(self, url):
|
||||
pass
|
||||
|
||||
# description
|
||||
video_description = get_element_by_id("eow-description", video_webpage)
|
||||
if video_description: video_description = clean_html(video_description.decode('utf8'))
|
||||
video_description = get_element_by_id("eow-description", video_webpage.decode('utf8'))
|
||||
if video_description: video_description = clean_html(video_description)
|
||||
else: video_description = ''
|
||||
|
||||
# closed captions
|
||||
@ -1055,8 +1055,8 @@ def _real_extract(self, url, new_video=True):
|
||||
video_thumbnail = config["video"]["thumbnail"]
|
||||
|
||||
# Extract video description
|
||||
video_description = get_element_by_id("description", webpage)
|
||||
if video_description: video_description = clean_html(video_description.decode('utf8'))
|
||||
video_description = get_element_by_id("description", webpage.decode('utf8'))
|
||||
if video_description: video_description = clean_html(video_description)
|
||||
else: video_description = ''
|
||||
|
||||
# Extract upload date
|
||||
|
@ -73,7 +73,7 @@ def htmlentity_transform(matchobj):
|
||||
# Unknown entity in name, return its literal representation
|
||||
return (u'&%s;' % entity)
|
||||
|
||||
|
||||
HTMLParser.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 IDParser(HTMLParser.HTMLParser):
|
||||
"""Modified HTMLParser that isolates a tag with the specified id"""
|
||||
def __init__(self, id):
|
||||
@ -83,8 +83,17 @@ def __init__(self, id):
|
||||
self.depth = {}
|
||||
self.html = None
|
||||
self.watch_startpos = False
|
||||
self.error_count = 0
|
||||
HTMLParser.HTMLParser.__init__(self)
|
||||
|
||||
def error(self, message):
|
||||
print self.getpos()
|
||||
if self.error_count > 10 or self.started:
|
||||
raise HTMLParser.HTMLParseError(message, self.getpos())
|
||||
self.rawdata = '\n'.join(self.html.split('\n')[self.getpos()[0]:]) # skip one line
|
||||
self.error_count += 1
|
||||
self.goahead(1)
|
||||
|
||||
def loads(self, html):
|
||||
self.html = html
|
||||
self.feed(html)
|
||||
|
Loading…
Reference in New Issue
Block a user