def getSerialsListByLetter(self, baseUrl, cat, letter):
letter = letter.replace(' ', '')
printDBG("getSerialsListByLetter start letter=%s" % letter)
sts, data = self.cm.getPage(baseUrl)
if False == sts:
printDBG("getSerialsListByLetter problem with getPage[%s]" %
baseUrl)
return
sts, data = CParsingHelper.getDataBeetwenMarkers(
data, 'id="letter_%s">' % letter, '</ul>', False)
if False == sts:
printDBG("getSerialsListByLetter problem no data beetween markers")
return
data = re.compile(
'<a href="([^"]+?)" class="pl-corners">(.+?)</a>').findall(data)
if len(data) > 0:
for i in range(len(data)):
title = remove_html_markup(data[i][1])
url = self.MAINURL + data[i][0].strip()
params = {
'name': 'category',
'category': cat,
'title': title,
'url': url
}
self.addDir(params)
def listCategories(self, url, cat):
printDBG("listCategories for url[%s] cat[%s]" % (url, cat))
# add all item
params = {'category': cat, 'title': '--Wszystkie--', 'cat_id': ''}
self.addDir(params)
sts, data = self.cm.getPage(url)
if not sts: return
sts, data = CParsingHelper.getDataBeetwenMarkers(
data, "<div class='window_title'>", "<div class='footer'>")
if not sts: return False
data = data.split("<div class='list_title'>")
if len(data) > 1:
del data[0]
for item in data:
# cat_id: match.group(2) & title: match.group(1) & img: self.MAINURL + match.group(3)
match = re.search(
"<b>([^<]+?)</b></a></div><a href='[^']*?category=([0-9]+?)'><img[^>]*?src='([^']+?)'",
item)
if not match: continue
# plot
printDBG('AAAAAAAAAAAAAAAAAAAAAAAAAAAAAA: [%s]' %
match.group(2))
plot = CParsingHelper.removeDoubles(
remove_html_markup(item, ' ').replace(match.group(1), ''),
' ')
params = {
'category': cat,
'title': match.group(1),
'cat_id': match.group(2),
'icon': self.MAINURL + "/" + match.group(3),
'plot': plot
}
self.addDir(params)
def listVideos(self, baseUrl, cat, cat_id, sort, page, search_pattern=''):
url = baseUrl % (cat_id, sort, page)
printDBG("listVideos for url[%s]" % url)
sts, data = self.cm.getPage(url)
if not sts: return
nextPage = False
if -1 < data.find("class='black'>»</a>"):
nextPage = True
sts, data = CParsingHelper.getDataBeetwenMarkers(
data, "<div class='window_title'>", "<div class='footer'>")
if not sts: return False
data = data.split("<div class='list' style='width: 173px;'>")
if len(data) > 1:
del data[0]
for item in data:
# vid_hash & img
match = re.search(
"href='([0-9a-fA-F]{32})'[^>]*?><img[^>]*?src='([^']+?)'",
item)
if not match: continue
vid_hash = match.group(1)
img = self.MAINURL + "/" + match.group(2)
if not match: continue
# title
match = re.search(
"<div class='list_title'><a href='%s'>([^<]+?)</a></div>" %
vid_hash, item)
if not match: continue
title = match.group(1)
# plot
plot = CParsingHelper.removeDoubles(
remove_html_markup(item, ' ').replace(title, ''), ' ')
params = {
'title': title,
'url': self.MAINURL + "/" + vid_hash,
'icon': img,
'plot': plot
}
if 'Rozmiar:' in item:
continue
else:
self.playVideo(params)
if nextPage:
params = {
'title': "Następna strona",
'category': cat,
'cat_id': cat_id,
'sort': sort,
'page': str(int(page) + 1),
'search_pattern': search_pattern
}
self.addDir(params)
def getSearchResult(self, baseUrl, cat, page):
printDBG("getSearchResult for url[%s] page[%s]" % (baseUrl, page))
if 1 < int(page) != '1': url = baseUrl + page
else: url = baseUrl
sts, data = self.cm.getPage(url)
if not sts: return
nextPage = False
if -1 < data.find("class='pagination_next'"):
nextPage = True
sts, data = self.getDataBeetwenMarkers(data,
'<td valign="top">',
'<div class="menu_dol">',
withMarkers=False)
if not sts: return
data = data.split('<td valign="top">')
for item in data:
# url & title
match = re.search(
'<div class="video_title">[^<]*?<a href="([^"]+?)">([^<]+?)</a>',
item)
if match:
url = match.group(1)
title = match.group(2)
else:
continue
# img
match = re.search('src="([^"]+?)"', item)
if match: img = match.group(1)
else: img = ''
# plot
match = re.search('<div class="video_details">(.+?)</td>', item,
re.DOTALL)
if match:
plot = remove_html_markup(
match.group(1)) #.replace("</div>", " ")
else:
plot = ''
params = {'title': title, 'url': url, 'icon': img, 'plot': plot}
if 'Rozmiar:' in item:
continue
else:
self.playVideo(params)
if nextPage:
params = {
'title': "Następna strona",
'url': baseUrl,
'category': cat,
'page': str(int(page) + 1)
}
self.addDir(params)
def listVideos(self, baseUrl, cat, page):
printDBG("listVideos for url[%s] page[%s]" % (baseUrl, page))
if 1 < int(page) != '1': url = baseUrl + page
else: url = baseUrl
sts, data = self.cm.getPage(url)
if not sts: return
nextPage = False
if -1 < data.find("class='pagination_next'"):
nextPage = True
sts, data = self.getDataBeetwenMarkers(data,
'<td class="video">',
'</table>',
withMarkers=False)
if not sts: return
data = data.split('<td class="video">')
for item in data:
# url & title
match = re.search(
'class="video_title"><a href="([^"]+?)">([^<]+?)</a>', item)
if match:
url = match.group(1)
title = match.group(2)
else:
continue
# img
match = re.search('src="([^"]+?)"', item)
if match: img = match.group(1)
else: img = ''
# plot
match = re.search(
'<p style="margin:5px;" class="video_details">(.+?)</p>', item,
re.DOTALL)
if match: plot = remove_html_markup(match.group(1))
else: plot = ''
params = {'title': title, 'url': url, 'icon': img, 'plot': plot}
self.playVideo(params)
if nextPage:
params = {
'title': "Następna strona",
'url': baseUrl,
'category': cat,
'page': str(int(page) + 1)
}
self.addDir(params)
def getSerialsListByLetter(self, baseUrl, cat, letter):
letter = letter.replace(' ', '')
printDBG("getSerialsListByLetter start letter=%s" % letter)
sts, data = self.cm.getPage( baseUrl )
if False == sts:
printDBG("getSerialsListByLetter problem with getPage[%s]" % baseUrl)
return
sts, data = CParsingHelper.getDataBeetwenMarkers(data, 'id="letter_%s">' % letter, '</ul>', False)
if False == sts:
printDBG("getSerialsListByLetter problem no data beetween markers")
return
data = re.compile('<a href="([^"]+?)" class="pl-corners">(.+?)</a>').findall(data)
if len(data) > 0:
for i in range(len(data)):
title = remove_html_markup(data[i][1])
url = self.MAINURL + data[i][0].strip()
params = {'name':'category', 'category':cat, 'title':title, 'url':url}
self.addDir(params)
def getSearchResult(self, baseUrl, cat, page):
printDBG("getSearchResult for url[%s] page[%s]" % (baseUrl, page))
if 1 < int(page) != '1': url = baseUrl + page
else: url = baseUrl
sts, data = self.cm.getPage(url)
if not sts: return
nextPage = False
if -1 < data.find("class='pagination_next'"):
nextPage = True
sts, data = self.getDataBeetwenMarkers(data, '<td valign="top">', '<div class="menu_dol">', withMarkers = False)
if not sts: return
data = data.split('<td valign="top">')
for item in data:
# url & title
match = re.search('<div class="video_title">[^<]*?<a href="([^"]+?)">([^<]+?)</a>', item)
if match:
url = match.group(1)
title = match.group(2)
else: continue
# img
match = re.search('src="([^"]+?)"', item)
if match: img = match.group(1)
else: img = ''
# plot
match = re.search('<div class="video_details">(.+?)</td>', item, re.DOTALL)
if match: plot = remove_html_markup(match.group(1)) #.replace("</div>", " ")
else: plot = ''
params = { 'title': title, 'url': url, 'icon': img, 'plot': plot}
if 'Rozmiar:' in item:
continue
else:
self.playVideo(params)
if nextPage:
params = {'title': "Następna strona", 'url': baseUrl, 'category': cat, 'page':str(int(page)+1)}
self.addDir(params)
def listCategories(self, url, cat):
printDBG("listCategories for url[%s] cat[%s]" % (url, cat))
# add all item
params = {'category': cat, 'title': '--Wszystkie--' , 'cat_id': ''}
self.addDir(params)
sts, data = self.cm.getPage(url)
if not sts: return
sts, data = CParsingHelper.getDataBeetwenMarkers(data, "<div class='window_title'>", "<div class='footer'>")
if not sts: return False
data = data.split("<div class='list_title'>")
if len(data) > 1:
del data[0]
for item in data:
# cat_id: match.group(2) & title: match.group(1) & img: self.MAINURL + match.group(3)
match = re.search("<b>([^<]+?)</b></a></div><a href='[^']*?category=([0-9]+?)'><img[^>]*?src='([^']+?)'", item)
if not match: continue
# plot
printDBG('AAAAAAAAAAAAAAAAAAAAAAAAAAAAAA: [%s]' % match.group(2))
plot = CParsingHelper.removeDoubles(remove_html_markup(item, ' ').replace(match.group(1), ''), ' ')
params = {'category': cat, 'title': match.group(1) , 'cat_id': match.group(2) , 'icon': self.MAINURL + "/" + match.group(3), 'plot':plot}
self.addDir(params)
def listVideos(self, baseUrl, cat, cat_id, sort, page, search_pattern = ''):
url = baseUrl % (cat_id, sort, page)
printDBG("listVideos for url[%s]" % url)
sts, data = self.cm.getPage(url)
if not sts: return
nextPage = False
if -1 < data.find("class='black'>»</a>"):
nextPage = True
sts, data = CParsingHelper.getDataBeetwenMarkers(data, "<div class='window_title'>", "<div class='footer'>")
if not sts: return False
data = data.split("<div class='list' style='width: 173px;'>")
if len(data) > 1:
del data[0]
for item in data:
# vid_hash & img
match = re.search("href='([0-9a-fA-F]{32})'[^>]*?><img[^>]*?src='([^']+?)'", item)
if not match: continue
vid_hash = match.group(1)
img = self.MAINURL + "/" + match.group(2)
if not match: continue
# title
match = re.search("<div class='list_title'><a href='%s'>([^<]+?)</a></div>" % vid_hash, item)
if not match: continue
title = match.group(1)
# plot
plot = CParsingHelper.removeDoubles(remove_html_markup(item, ' ').replace(title, ''), ' ')
params = { 'title': title, 'url': self.MAINURL + "/" +vid_hash, 'icon': img, 'plot': plot}
if 'Rozmiar:' in item:
continue
else:
self.playVideo(params)
if nextPage:
params = {'title': "Następna strona", 'category': cat, 'cat_id':cat_id, 'sort':sort, 'page':str(int(page)+1), 'search_pattern':search_pattern}
self.addDir(params)
def listVideos(self, baseUrl, cat, page):
printDBG("listVideos for url[%s] page[%s]" % (baseUrl, page))
if 1 < int(page) != '1': url = baseUrl + page
else: url = baseUrl
sts, data = self.cm.getPage(url)
if not sts: return
nextPage = False
if -1 < data.find("class='pagination_next'"):
nextPage = True
sts, data = self.getDataBeetwenMarkers(data, '<td class="video">', '</table>', withMarkers = False)
if not sts: return
data = data.split('<td class="video">')
for item in data:
# url & title
match = re.search('class="video_title"><a href="([^"]+?)">([^<]+?)</a>', item)
if match:
url = match.group(1)
title = match.group(2)
else: continue
# img
match = re.search('src="([^"]+?)"', item)
if match: img = match.group(1)
else: img = ''
# plot
match = re.search('<p style="margin:5px;" class="video_details">(.+?)</p>', item, re.DOTALL)
if match: plot = remove_html_markup(match.group(1))
else: plot = ''
params = { 'title': title, 'url': url, 'icon': img, 'plot': plot}
self.playVideo(params)
if nextPage:
params = {'title': "Następna strona", 'url': baseUrl, 'category': cat, 'page':str(int(page)+1)}
self.addDir(params)
def parseListBase(self, data, type='video'):
printDBG("parseListBase----------------")
urlPatterns = { 'video' : ['video' , 'href="[ ]*?(/watch\?v=[^"]+?)"' , ''],
'channel' : ['category', 'href="(/[^"]+?)"' , ''],
'playlist' : ['category', 'list=([^"]+?)"' , '/playlist?list='],
'movie' : ['video' , 'data-context-item-id="([^"]+?)"' , '/watch?v='],
'live' : ['video' , 'href="(/watch\?v=[^"]+?)"' , ''],
'tray' : ['video' , 'data-video-id="([^"]+?)"' , '/watch?v='], }
currList = []
for i in range(len(data)):
#printDBG("+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++")
# get requaired params
url = urlPatterns[type][2] + self.getAttributes(urlPatterns[type][1], data[i])
# get title
title = '' #self.getAttributes('title="([^"]+?)"', data[i])
if '' == title: title = self.getAttributes('data-context-item-title="([^"]+?)"', data[i])
if '' == title: title = self.getAttributes('data-video-title="([^"]+?)"', data[i])
if '' == title: sts,title = CParsingHelper.getDataBeetwenMarkers(data[i], '<h3 class="yt-lockup-title">', '</h3>', False)
if '' == title: sts,title = CParsingHelper.getDataBeetwenReMarkers(data[i], re.compile('<span [^>]*?class="title[^>]*?>'), re.compile('</span>'), False)
if '' == title: sts,title = CParsingHelper.getDataBeetwenReMarkers(data[i], re.compile('class="pl-video-title-link[^>]*?>'), re.compile('<'), False)
if '' == title:
titleMarker = self.cm.ph.getSearchGroups(data[i], '(<[^">]+?"yt-lockup-title[^"]*?"[^>]*?>)')[0]
if '' != titleMarker:
tidx = titleMarker.find(' ')
if tidx > 0:
tmarker = titleMarker[1:tidx]
title = self.cm.ph.getDataBeetwenMarkers(data[i], titleMarker, '</%s>' % tmarker)[1]
if '' != title: title = CParsingHelper.removeDoubles(remove_html_markup(title, ' '), ' ')
img = self.getAttributes('data-thumb="([^"]+?\.jpg)"', data[i])
if '' == img: img = self.getAttributes('src="([^"]+?\.jpg)"', data[i])
time = self.getAttributes('data-context-item-time="([^"]+?)"', data[i])
if '' == time: time = self.getAttributes('class="video-time">([^<]+?)</span>', data[i])
if '' == time: sts, time = CParsingHelper.getDataBeetwenReMarkers(data[i], re.compile('pl-video-time"[^>]*?>'), re.compile('<'), False)
if '' == time: sts, time = CParsingHelper.getDataBeetwenReMarkers(data[i], re.compile('timestamp"[^>]*?>'), re.compile('<'), False)
time = time.strip()
# desc
sts,desc = CParsingHelper.getDataBeetwenReMarkers(data[i], re.compile('class="video-description[^>]+?>'), re.compile('</p>'), False)
if '' == desc: sts,desc = CParsingHelper.getDataBeetwenReMarkers(data[i], re.compile('class="yt-lockup-description[^>]+?>'), re.compile('</div>'), False)
desc = CParsingHelper.removeDoubles(remove_html_markup(desc, ' '), ' ')
urlTmp = url.split(';')
if len(urlTmp) > 0: url = urlTmp[0]
if type == 'video': url = url.split('&')[0]
# printDBG('url [%s] ' % url)
# printDBG('title [%s] ' % title)
# printDBG('img [%s] ' % img)
# printDBG('time [%s] ' % time)
# printDBG('desc [%s] ' % desc)
if title != '' and url != '' and img != '':
correctUrlTab = [url, img]
for i in range(len(correctUrlTab)):
if not correctUrlTab[i].startswith('http:') and not correctUrlTab[i].startswith('https:'):
if correctUrlTab[i].startswith("//"):
correctUrlTab[i] = 'http:' + correctUrlTab[i]
else:
correctUrlTab[i] = 'http://www.youtube.com' + correctUrlTab[i]
else:
if correctUrlTab[i].startswith('https:'):
correctUrlTab[i] = "http:" + correctUrlTab[i][6:]
title = clean_html(title.decode("utf-8")).encode("utf-8")
desc = clean_html(desc.decode("utf-8")).encode("utf-8")
params = {'type': urlPatterns[type][0], 'category': type, 'title': title, 'url': correctUrlTab[0], 'icon': correctUrlTab[1], 'time': time, 'desc': desc}
currList.append(params)
return currList
def parseListBase(self, data, type='video'):
printDBG("parseListBase----------------")
urlPatterns = {
'video': ['video', 'href="[ ]*?(/watch\?v=[^"]+?)"', ''],
'channel': ['category', 'href="(/[^"]+?)"', ''],
'playlist': ['category', 'list=([^"]+?)"', '/playlist?list='],
'movie': ['video', 'data-context-item-id="([^"]+?)"', '/watch?v='],
'live': ['video', 'href="(/watch\?v=[^"]+?)"', ''],
'tray': ['video', 'data-video-id="([^"]+?)"', '/watch?v='],
}
currList = []
for i in range(len(data)):
#printDBG("+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++")
# get requaired params
url = urlPatterns[type][2] + self.getAttributes(
urlPatterns[type][1], data[i])
# get title
title = '' #self.getAttributes('title="([^"]+?)"', data[i])
if '' == title:
title = self.getAttributes(
'data-context-item-title="([^"]+?)"', data[i])
if '' == title:
title = self.getAttributes('data-video-title="([^"]+?)"',
data[i])
if '' == title:
sts, title = CParsingHelper.getDataBeetwenMarkers(
data[i], '<h3 class="yt-lockup-title">', '</h3>', False)
if '' == title:
sts, title = CParsingHelper.getDataBeetwenReMarkers(
data[i], re.compile('<span [^>]*?class="title[^>]*?>'),
re.compile('</span>'), False)
if '' == title:
sts, title = CParsingHelper.getDataBeetwenReMarkers(
data[i], re.compile('class="pl-video-title-link[^>]*?>'),
re.compile('<'), False)
if '' != title:
title = CParsingHelper.removeDoubles(
remove_html_markup(title, ' '), ' ')
img = self.getAttributes('data-thumb="([^"]+?\.jpg)"', data[i])
if '' == img:
img = self.getAttributes('src="([^"]+?\.jpg)"', data[i])
time = self.getAttributes('data-context-item-time="([^"]+?)"',
data[i])
if '' == time:
time = self.getAttributes('class="video-time">([^<]+?)</span>',
data[i])
if '' == time:
sts, time = CParsingHelper.getDataBeetwenReMarkers(
data[i], re.compile('pl-video-time"[^>]*?>'),
re.compile('<'), False)
if '' == time:
sts, time = CParsingHelper.getDataBeetwenReMarkers(
data[i], re.compile('timestamp"[^>]*?>'), re.compile('<'),
False)
time = time.strip()
# desc
sts, desc = CParsingHelper.getDataBeetwenReMarkers(
data[i], re.compile('class="video-description[^>]+?>'),
re.compile('</p>'), False)
if '' == desc:
sts, desc = CParsingHelper.getDataBeetwenReMarkers(
data[i], re.compile('class="yt-lockup-description[^>]+?>'),
re.compile('</div>'), False)
desc = CParsingHelper.removeDoubles(remove_html_markup(desc, ' '),
' ')
urlTmp = url.split(';')
if len(urlTmp) > 0: url = urlTmp[0]
if type == 'video': url = url.split('&')[0]
# printDBG('url [%s] ' % url)
# printDBG('title [%s] ' % title)
# printDBG('img [%s] ' % img)
# printDBG('time [%s] ' % time)
# printDBG('desc [%s] ' % desc)
if title != '' and url != '' and img != '':
correctUrlTab = [url, img]
for i in range(len(correctUrlTab)):
if not correctUrlTab[i].startswith(
'http:') and not correctUrlTab[i].startswith(
'https:'):
if correctUrlTab[i].startswith("//"):
correctUrlTab[i] = 'http:' + correctUrlTab[i]
else:
correctUrlTab[
i] = 'http://www.youtube.com' + correctUrlTab[i]
else:
if correctUrlTab[i].startswith('https:'):
correctUrlTab[i] = "http:" + correctUrlTab[i][6:]
title = clean_html(title.decode("utf-8")).encode("utf-8")
desc = clean_html(desc.decode("utf-8")).encode("utf-8")
params = {
'type': urlPatterns[type][0],
'category': type,
'title': title,
'url': correctUrlTab[0],
'icon': correctUrlTab[1],
'time': time,
'desc': desc
}
currList.append(params)
return currList
def parseListBase(self, data, type='video'):
printDBG("parseListBase----------------")
urlPatterns = {
'video': ['video', 'href="[ ]*?(/watch\?v=[^"]+?)"', ''],
'channel': ['category', 'href="(/[^"]+?)"', ''],
'playlist': ['category', 'list=([^"]+?)"', '/playlist?list='],
'movie': ['video', 'data-context-item-id="([^"]+?)"', '/watch?v='],
'live': ['video', 'href="(/watch\?v=[^"]+?)"', ''],
'tray': ['video', 'data-video-id="([^"]+?)"', '/watch?v='],
}
currList = []
for i in range(len(data)):
#printDBG("+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++")
# get requaired params
url = urlPatterns[type][2] + self.getAttributes(
urlPatterns[type][1], data[i])
# get title
title = '' #self.getAttributes('title="([^"]+?)"', data[i])
if '' == title:
title = self.getAttributes(
'data-context-item-title="([^"]+?)"', data[i])
if '' == title:
title = self.getAttributes('data-video-title="([^"]+?)"',
data[i])
if '' == title:
sts, title = CParsingHelper.getDataBeetwenMarkers(
data[i], '<h3 class="yt-lockup-title">', '</h3>', False)
if '' == title:
sts, title = CParsingHelper.getDataBeetwenReMarkers(
data[i], re.compile('<span [^>]*?class="title[^>]*?>'),
re.compile('</span>'), False)
if '' == title:
sts, title = CParsingHelper.getDataBeetwenReMarkers(
data[i], re.compile('class="pl-video-title-link[^>]*?>'),
re.compile('<'), False)
if '' == title:
titleMarker = self.cm.ph.getSearchGroups(
data[i], '(<[^">]+?"yt-lockup-title[^"]*?"[^>]*?>)')[0]
if '' != titleMarker:
tidx = titleMarker.find(' ')
if tidx > 0:
tmarker = titleMarker[1:tidx]
title = self.cm.ph.getDataBeetwenMarkers(
data[i], titleMarker, '</%s>' % tmarker)[1]
if '' != title:
title = CParsingHelper.removeDoubles(
remove_html_markup(title, ' '), ' ')
img = self.getAttributes('data-thumb="([^"]+?\.jpg[^"]*?)"',
data[i])
if '' == img:
img = self.getAttributes('src="([^"]+?\.jpg[^"]*?)"', data[i])
time = self.getAttributes('data-context-item-time="([^"]+?)"',
data[i])
if '' == time:
time = self.getAttributes('class="video-time">([^<]+?)</span>',
data[i])
if '' == time:
sts, time = CParsingHelper.getDataBeetwenReMarkers(
data[i], re.compile('pl-video-time"[^>]*?>'),
re.compile('<'), False)
if '' == time:
sts, time = CParsingHelper.getDataBeetwenReMarkers(
data[i], re.compile('timestamp"[^>]*?>'), re.compile('<'),
False)
time = time.strip()
# desc
descTab = []
desc = self.cm.ph.getDataBeetwenMarkers(
data[i], '<div class="yt-lockup-meta', '</div>')[1]
if desc != '': descTab.append(desc)
desc = self.cm.ph.getDataBeetwenMarkers(
data[i], '<span class="formatted-video-count', '</span>')[1]
if desc != '': descTab.append(desc)
desc = self.cm.ph.getDataBeetwenReMarkers(
data[i], re.compile('class="video-description[^>]+?>'),
re.compile('</p>'), False)[1]
if '' == desc:
desc = self.cm.ph.getDataBeetwenReMarkers(
data[i], re.compile('class="yt-lockup-description[^>]+?>'),
re.compile('</div>'), False)[1]
if desc != '': descTab.append(desc)
newDescTab = []
for desc in descTab:
desc = self.cm.ph.removeDoubles(remove_html_markup(desc, ' '),
' ')
desc = clean_html(desc).strip()
if desc != '':
newDescTab.append(desc)
urlTmp = url.split(';')
if len(urlTmp) > 0: url = urlTmp[0]
if type == 'video': url = url.split('&')[0]
#printDBG("#####################################")
#printDBG('url [%s] ' % url)
#printDBG('title [%s] ' % title)
#printDBG('img [%s] ' % img)
#printDBG('time [%s] ' % time)
#printDBG('desc [%s] ' % desc)
if title != '' and url != '' and img != '':
correctUrlTab = [url, img]
for i in range(len(correctUrlTab)):
if not correctUrlTab[i].startswith(
'http:') and not correctUrlTab[i].startswith(
'https:'):
if correctUrlTab[i].startswith("//"):
correctUrlTab[i] = 'http:' + correctUrlTab[i]
else:
correctUrlTab[
i] = 'http://www.youtube.com' + correctUrlTab[i]
else:
if correctUrlTab[i].startswith('https:'):
correctUrlTab[i] = "http:" + correctUrlTab[i][6:]
title = clean_html(title)
params = {
'type': urlPatterns[type][0],
'category': type,
'title': title,
'url': correctUrlTab[0],
'icon': correctUrlTab[1].replace('&', '&'),
'time': time,
'desc': '[/br]'.join(newDescTab)
}
currList.append(params)
return currList