def parse_resource(self, response):
logging.log(logging.INFO, "parse_resource:%s" % response.request.url)
m_item = response.request.meta['m_item']
vtitle = response.request.meta['vtitle']
vnum = response.request.meta['vnum']
vitems = []
for x in ['Torrent magnet link', 'Download torrent file']:
vurls = response.xpath('//table[@class="data"]//tr/td[1]//a[@title="%s"]/@href' % x).extract()
rtitles = response.xpath('//table[@class="data"]//tr/td[1]//a[@title="%s"]/../../div[@class="torrentname"]/div/a/text()' % x).extract()
if not vurls:
continue
vurl = vurls[0]
rtitle = rtitles[0]
if vurl.startswith('//'):
vurl = 'https:' + vurl
protocol = extract_protocol(vurl)
if protocol in self.protocol_map and protocol != 'http':
v_item = VideoItem()
v_item['url'] = vurl
v_item['title'] = rtitle
v_item['vnum'] = vnum
#v_item['vtitle'] = vtitle
v_item['cont_id'] = md5(vurl).hexdigest()
v_item['protocol_id'] = self.protocol_map[protocol]
if protocol == 'magnet':
v_item['tor_ih'] = extract_info_ih(vurl)
vitems.append(v_item)
mvitem = MediaVideoItem()
mvitem["media"] = m_item
mvitem['video'] = vitems
yield mvitem
def parse_all_episode(self, response):
logging.log(logging.INFO,
"parse_all_episode:%s" % response.request.url)
try:
mtitle = response.xpath(
'//table[@class="doublecelltable"]//tr/td[1]/h1/text()'
).extract()[0]
imdb_url = response.xpath(
'//div[@class="torrentMediaInfo"]/div[@class="dataList"]/ul/li/strong[text()="IMDb link:"]/../a/@href'
).extract()[0]
imdb = extract_imdb(imdb_url)
# tv
seasons = response.xpath(
'//table[@class="doublecelltable"]//tr/td[1]/h3')
for season in seasons:
snums = season.xpath('./text()').re('\d+')
if snums:
snum = int(snums[0])
resources = season.xpath(
'./following-sibling::div[1]/div/div[@class="infoList versionsFolded"]/a[@class="infoListCut"]'
)
for r in resources:
vnums = r.xpath(
'./span[@class="versionsEpNo"]/text()').re('\d+')
vtitles = r.xpath(
'./span[@class="versionsEpName"]/text()').extract(
)
if not vnums or not vtitles:
continue
vnum = int(vnums[0])
if vnum <= 0:
continue
vtitle = vtitles[0]
episode_nums = r.xpath('./@onclick').re('\d+')
if not episode_nums:
continue
episode_num = episode_nums[0]
m_item = MediaItem()
m_item['title'] = mtitle + '_Season' + str(snum)
m_item['url'] = response.request.url
m_item['site_id'] = self.site_id
#m_item['imdb'] = imdb + '|' + str(snum)
m_item['cont_id'] = imdb + '|' + str(snum)
req = Request(url=self.url_getepisode % episode_num,
callback=self.parse_resource,
meta={
'm_item': m_item,
'vtitle': vtitle,
'vnum': vnum
})
yield req
# movie
vitems = []
dids = response.xpath(
'//div[@class="tabs tabSwitcher"]/div[@id]/@id').extract()
for did in dids:
for x in ['Torrent magnet link', 'Download torrent file']:
vurls = response.xpath(
'//div[@id="%s"]/table//tr[@id]/td[1]/div[1]/a[@title="%s"]/@href'
% (did, x)).extract()
vtitles = response.xpath(
'//div[@id="%s"]/table//tr[@id]/td[1]/div[1]/a[@title="%s"]/../../div[@class="torrentname"]/div/a/text()'
% (did, x)).extract()
if not vurls or not vtitles:
continue
vurl = vurls[0]
vtitle = vtitles[0]
if vurl.startswith('//'):
vurl = 'https:' + vurl
protocol = extract_protocol(vurl)
if protocol in self.protocol_map and protocol != 'http':
v_item = VideoItem()
v_item['url'] = vurl
v_item['title'] = vtitle
v_item['cont_id'] = md5(vurl).hexdigest()
v_item['protocol_id'] = self.protocol_map[protocol]
if protocol == 'magnet':
v_item['tor_ih'] = extract_info_ih(vurl)
vitems.append(v_item)
if vitems:
m_item = MediaItem()
m_item['title'] = mtitle
m_item['url'] = response.request.url
m_item['site_id'] = self.site_id
#m_item['imdb'] = imdb
m_item['cont_id'] = imdb
mvitem = MediaVideoItem()
mvitem["media"] = m_item
mvitem['video'] = vitems
yield mvitem
except Exception, e:
logging.log(logging.ERROR, traceback.format_exc())