def cleanHtmlStr(str):
return CParsingHelper.cleanHtmlStr(str)
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.cleanHtmlStr(title)
if i == 0:
printDBG(data[i])
img = self.getAttributes('data-thumb="([^"]+?\.jpg[^"]*?)"',
data[i])
if '' == img:
img = self.getAttributes('src="([^"]+?\.jpg[^"]*?)"', data[i])
if '' == img:
img = self.getAttributes('<img[^>]+?data\-thumb="([^"]+?)"',
data[i])
if '' == img:
img = self.getAttributes('<img[^>]+?src="([^"]+?)"', data[i])
if '.gif' in img: img = ''
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 = CParsingHelper.cleanHtmlStr(desc)
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 = CParsingHelper.cleanHtmlStr(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
