removed the undocumented HTMLParser.unescape, replaced with _unescapeHTML; fixed a bug in the use of _unescapeHTML (missing _, from d6a9615347)

pull/329/head
Filippo Valsorda - Campagna 13 years ago
parent c6f45d4314
commit 781cc523af

@ -308,13 +308,13 @@ def clean_html(html):
# Strip html tags # Strip html tags
html = re.sub('<.*?>', '', html) html = re.sub('<.*?>', '', html)
# Replace html entities # Replace html entities
html = re.sub(ur'(?u)&(.+?);', htmlentity_transform, html) html = _unescapeHTML(html)
return html return html
def sanitize_title(utitle): def sanitize_title(utitle):
"""Sanitizes a video title so it could be used as part of a filename.""" """Sanitizes a video title so it could be used as part of a filename."""
utitle = re.sub(ur'(?u)&(.+?);', htmlentity_transform, utitle) utitle = _unescapeHTML(utitle)
return utitle.replace(unicode(os.sep), u'%') return utitle.replace(unicode(os.sep), u'%')
@ -371,8 +371,8 @@ def _unescapeHTML(s):
""" """
assert type(s) == type(u'') assert type(s) == type(u'')
htmlParser = HTMLParser.HTMLParser() result = re.sub(ur'(?u)&(.+?);', htmlentity_transform, s)
return htmlParser.unescape(s) return result
def _encodeFilename(s): def _encodeFilename(s):
""" """
@ -1324,8 +1324,8 @@ class YoutubeIE(InfoExtractor):
end = start + float(dur) end = start + float(dur)
start = "%02i:%02i:%02i,%03i" %(start/(60*60), start/60%60, start%60, start%1*1000) start = "%02i:%02i:%02i,%03i" %(start/(60*60), start/60%60, start%60, start%1*1000)
end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000) end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000)
caption = re.sub(ur'(?u)&(.+?);', htmlentity_transform, caption) caption = _unescapeHTML(caption)
caption = re.sub(ur'(?u)&(.+?);', htmlentity_transform, caption) # double cycle, inentional caption = _unescapeHTML(caption) # double cycle, inentional
srt += str(n) + '\n' srt += str(n) + '\n'
srt += start + ' --> ' + end + '\n' srt += start + ' --> ' + end + '\n'
srt += caption + '\n\n' srt += caption + '\n\n'
@ -2143,7 +2143,7 @@ class YahooIE(InfoExtractor):
self._downloader.trouble(u'ERROR: Unable to extract media URL') self._downloader.trouble(u'ERROR: Unable to extract media URL')
return return
video_url = urllib.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8') video_url = urllib.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8')
video_url = re.sub(r'(?u)&(.+?);', htmlentity_transform, video_url) video_url = _unescapeHTML(video_url)
try: try:
# Process video information # Process video information
@ -3410,11 +3410,11 @@ class EscapistIE(InfoExtractor):
return return
descMatch = re.search('<meta name="description" content="([^"]*)"', webPage) descMatch = re.search('<meta name="description" content="([^"]*)"', webPage)
description = unescapeHTML(descMatch.group(1)) description = _unescapeHTML(descMatch.group(1))
imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage) imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage)
imgUrl = unescapeHTML(imgMatch.group(1)) imgUrl = _unescapeHTML(imgMatch.group(1))
playerUrlMatch = re.search('<meta property="og:video" content="([^"]*)"', webPage) playerUrlMatch = re.search('<meta property="og:video" content="([^"]*)"', webPage)
playerUrl = unescapeHTML(playerUrlMatch.group(1)) playerUrl = _unescapeHTML(playerUrlMatch.group(1))
configUrlMatch = re.search('config=(.*)$', playerUrl) configUrlMatch = re.search('config=(.*)$', playerUrl)
configUrl = urllib2.unquote(configUrlMatch.group(1)) configUrl = urllib2.unquote(configUrlMatch.group(1))
@ -3966,20 +3966,20 @@ class StanfordOpenClassroomIE(InfoExtractor):
m = re.search('<h1>([^<]+)</h1>', coursepage) m = re.search('<h1>([^<]+)</h1>', coursepage)
if m: if m:
info['title'] = unescapeHTML(m.group(1)) info['title'] = _unescapeHTML(m.group(1))
else: else:
info['title'] = info['id'] info['title'] = info['id']
info['stitle'] = _simplify_title(info['title']) info['stitle'] = _simplify_title(info['title'])
m = re.search('<description>([^<]+)</description>', coursepage) m = re.search('<description>([^<]+)</description>', coursepage)
if m: if m:
info['description'] = unescapeHTML(m.group(1)) info['description'] = _unescapeHTML(m.group(1))
links = _orderedSet(re.findall('<a href="(VideoPage.php\?[^"]+)">', coursepage)) links = _orderedSet(re.findall('<a href="(VideoPage.php\?[^"]+)">', coursepage))
info['list'] = [ info['list'] = [
{ {
'type': 'reference', 'type': 'reference',
'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(vpage), 'url': 'http://openclassroom.stanford.edu/MainFolder/' + _unescapeHTML(vpage),
} }
for vpage in links] for vpage in links]
@ -4007,7 +4007,7 @@ class StanfordOpenClassroomIE(InfoExtractor):
info['list'] = [ info['list'] = [
{ {
'type': 'reference', 'type': 'reference',
'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(cpage), 'url': 'http://openclassroom.stanford.edu/MainFolder/' + _unescapeHTML(cpage),
} }
for cpage in links] for cpage in links]

@ -308,13 +308,13 @@ def clean_html(html):
# Strip html tags # Strip html tags
html = re.sub('<.*?>', '', html) html = re.sub('<.*?>', '', html)
# Replace html entities # Replace html entities
html = re.sub(ur'(?u)&(.+?);', htmlentity_transform, html) html = _unescapeHTML(html)
return html return html
def sanitize_title(utitle): def sanitize_title(utitle):
"""Sanitizes a video title so it could be used as part of a filename.""" """Sanitizes a video title so it could be used as part of a filename."""
utitle = re.sub(ur'(?u)&(.+?);', htmlentity_transform, utitle) utitle = _unescapeHTML(utitle)
return utitle.replace(unicode(os.sep), u'%') return utitle.replace(unicode(os.sep), u'%')
@ -371,8 +371,8 @@ def _unescapeHTML(s):
""" """
assert type(s) == type(u'') assert type(s) == type(u'')
htmlParser = HTMLParser.HTMLParser() result = re.sub(ur'(?u)&(.+?);', htmlentity_transform, s)
return htmlParser.unescape(s) return result
def _encodeFilename(s): def _encodeFilename(s):
""" """
@ -1324,8 +1324,8 @@ class YoutubeIE(InfoExtractor):
end = start + float(dur) end = start + float(dur)
start = "%02i:%02i:%02i,%03i" %(start/(60*60), start/60%60, start%60, start%1*1000) start = "%02i:%02i:%02i,%03i" %(start/(60*60), start/60%60, start%60, start%1*1000)
end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000) end = "%02i:%02i:%02i,%03i" %(end/(60*60), end/60%60, end%60, end%1*1000)
caption = re.sub(ur'(?u)&(.+?);', htmlentity_transform, caption) caption = _unescapeHTML(caption)
caption = re.sub(ur'(?u)&(.+?);', htmlentity_transform, caption) # double cycle, inentional caption = _unescapeHTML(caption) # double cycle, inentional
srt += str(n) + '\n' srt += str(n) + '\n'
srt += start + ' --> ' + end + '\n' srt += start + ' --> ' + end + '\n'
srt += caption + '\n\n' srt += caption + '\n\n'
@ -2143,7 +2143,7 @@ class YahooIE(InfoExtractor):
self._downloader.trouble(u'ERROR: Unable to extract media URL') self._downloader.trouble(u'ERROR: Unable to extract media URL')
return return
video_url = urllib.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8') video_url = urllib.unquote(mobj.group(1) + mobj.group(2)).decode('utf-8')
video_url = re.sub(r'(?u)&(.+?);', htmlentity_transform, video_url) video_url = _unescapeHTML(video_url)
try: try:
# Process video information # Process video information
@ -3410,11 +3410,11 @@ class EscapistIE(InfoExtractor):
return return
descMatch = re.search('<meta name="description" content="([^"]*)"', webPage) descMatch = re.search('<meta name="description" content="([^"]*)"', webPage)
description = unescapeHTML(descMatch.group(1)) description = _unescapeHTML(descMatch.group(1))
imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage) imgMatch = re.search('<meta property="og:image" content="([^"]*)"', webPage)
imgUrl = unescapeHTML(imgMatch.group(1)) imgUrl = _unescapeHTML(imgMatch.group(1))
playerUrlMatch = re.search('<meta property="og:video" content="([^"]*)"', webPage) playerUrlMatch = re.search('<meta property="og:video" content="([^"]*)"', webPage)
playerUrl = unescapeHTML(playerUrlMatch.group(1)) playerUrl = _unescapeHTML(playerUrlMatch.group(1))
configUrlMatch = re.search('config=(.*)$', playerUrl) configUrlMatch = re.search('config=(.*)$', playerUrl)
configUrl = urllib2.unquote(configUrlMatch.group(1)) configUrl = urllib2.unquote(configUrlMatch.group(1))
@ -3966,20 +3966,20 @@ class StanfordOpenClassroomIE(InfoExtractor):
m = re.search('<h1>([^<]+)</h1>', coursepage) m = re.search('<h1>([^<]+)</h1>', coursepage)
if m: if m:
info['title'] = unescapeHTML(m.group(1)) info['title'] = _unescapeHTML(m.group(1))
else: else:
info['title'] = info['id'] info['title'] = info['id']
info['stitle'] = _simplify_title(info['title']) info['stitle'] = _simplify_title(info['title'])
m = re.search('<description>([^<]+)</description>', coursepage) m = re.search('<description>([^<]+)</description>', coursepage)
if m: if m:
info['description'] = unescapeHTML(m.group(1)) info['description'] = _unescapeHTML(m.group(1))
links = _orderedSet(re.findall('<a href="(VideoPage.php\?[^"]+)">', coursepage)) links = _orderedSet(re.findall('<a href="(VideoPage.php\?[^"]+)">', coursepage))
info['list'] = [ info['list'] = [
{ {
'type': 'reference', 'type': 'reference',
'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(vpage), 'url': 'http://openclassroom.stanford.edu/MainFolder/' + _unescapeHTML(vpage),
} }
for vpage in links] for vpage in links]
@ -4007,7 +4007,7 @@ class StanfordOpenClassroomIE(InfoExtractor):
info['list'] = [ info['list'] = [
{ {
'type': 'reference', 'type': 'reference',
'url': 'http://openclassroom.stanford.edu/MainFolder/' + unescapeHTML(cpage), 'url': 'http://openclassroom.stanford.edu/MainFolder/' + _unescapeHTML(cpage),
} }
for cpage in links] for cpage in links]

Loading…
Cancel
Save