def get_data_cached(self, url, useCache, timeout, page = True):
markizalog.logDebug("getdata(%s,%s,%s,%s)..."%(url, useCache, timeout, page))
if useCache:
if timeout == -1:
return self.cache_request_special(url)
if timeout == 1:
return self.cache_request_1(url, page);
if timeout == 3:
return self.cache_request_3(url, page);
if timeout == 8:
return self.cache_request_8(url, page);
return self.cache_request_30(url, page);
else:
return read_page(url) if page else util.request(url)
def videoLink(self, url):
result = []
doc = read_page(url)
main = doc.find('main')
url = main.find('iframe')['src']
req = urllib2.Request(url)
req.add_header('User-Agent', _UserAgent_)
response = urllib2.urlopen(req)
httpdata = response.read()
response.close()
httpdata = httpdata.replace("\r", "").replace("\n",
"").replace("\t", "")
thumb = re.compile(
'<meta property="og:image" content="(.+?)">').findall(httpdata)
thumb = thumb[0] if len(thumb) > 0 else ''
desc = re.compile('<meta name="description" content="(.+?)">').findall(
httpdata)
desc = desc[0] if len(desc) > 0 else ''
name = re.compile(
'<meta property="og:title" content="(.+?)">').findall(httpdata)
name = name[0] if len(name) > 0 else '?'
renditions = re.compile('renditions: \[(.+?)\]').findall(httpdata)
if len(renditions) > 0:
renditions = re.compile('[\'\:](.+?)[\'\:]').findall(renditions[0])
bitrates = re.compile('src = {(.+?):(.+?)}').findall(httpdata)
if len(bitrates) > 0:
urls = re.compile('[\'\"](.+?)[\'\"]').findall(bitrates[0][1])
markizalog.logDebug('URLS=%s' % urls)
for num, url in enumerate(urls):
markizalog.logDebug('URL=%s\nNUM=%s' % (url, num))
if num < len(renditions):
result.append(self.addLink(renditions[num], url))
else:
result.append(self.addLink(name, url))
else:
markizalog.logError('Chyba - Video nejde prehrat')
return result
def episodes(self, url):
result = []
doc = read_page(url)
for article in doc.findAll(
'article', 'b-article b-article-text b-article-inline'):
url = article.a['href'].encode('utf-8')
title = article.a['title'].encode('utf-8')
thumb = article.a.div.img['data-original'].encode('utf-8')
result.append(self.addDir(title, url, 3))
for section in doc.findAll('section',
'b-main-section b-section-articles my-5'):
if section.div.h3.getText(" ").encode('utf-8') == 'Celé epizódy':
for article in section.findAll('article'):
url = article.a['href'].encode('utf-8')
title = 'Celé epizódy - ' + article.a['title'].encode(
'utf-8')
thumb = article.a.div.img['data-original'].encode('utf-8')
result.append(self.addDir(title, url, 3, thumb, 1))
if section.div.h3.getText(" ").encode(
'utf-8') == 'Mohlo by sa vám páčiť':
for article in section.findAll('article'):
url = article.a['href'].encode('utf-8')
title = 'Mohlo by sa vám páčiť - ' + article.a[
'title'].encode('utf-8')
thumb = article.a.div.img['data-original'].encode('utf-8')
result.append(self.addDir(title, url, 3))
if section.div.h3.getText(" ").encode('utf-8') == 'Zo zákulisia':
for article in section.findAll('article'):
url = article.a['href'].encode('utf-8')
title = 'Zo zákulisia - ' + article.a['title'].encode(
'utf-8')
thumb = article.a.div.img['data-original'].encode('utf-8')
result.append(self.addDir(title, url, 3))
return result
def list(self, url):
result = []
url, mode = self.getMode(url)
markizalog.logDebug('list hit mode=%s, url=%s' % (mode, url))
if mode == 5:
# az
doc = read_page(url)
for article in doc.findAll('article'):
url = article.a['href'].encode('utf-8')
title = article.a['title'].encode('utf-8')
thumb = article.a.div.img['data-original'].encode('utf-8')
result.append(self.addDir(title, url, 2))
elif mode == 2:
# episodes
result = self.episodes(url)
pass
elif mode == 9:
# @TODO
# top
pass
elif mode == 8:
# @TODO
# new epizody
pass
elif mode == 6:
# @TODO
# najsledovanejsie
pass
elif mode == 7:
# @TODO
# odporucane
pass
elif mode == 3:
# @TODO
# video link
result = self.videoLink(url)
return result
def cache_request_30(self, url, page):
markizalog.logDebug("NOT CACHED REQUEST")
return read_page(url) if page else util.request(url)
def cache_request_special(self, url):
markizalog.logDebug("NOT CACHED REQUEST")
return read_page(url)