def detail_parse_by_subclass(self,url,page):
res = self.parser.get_parse_data(url,page)
urllist=[]
it = Item()
for l in res['list']:
li = l['li']
if "地区:" in li:
it.location = li.replace("地区:",'')
if "年份:" in li:
it.date = li.replace("年份:",'')
if "导演:" in li:
it.director = li.replace("导演:",'')
if "主演:" in li:
it.actors = li.replace("主演:",'')
it.url = url
quality = {}
for tinfo in res['tinfo']:
qs = tinfo['quality']
if '720p' in qs:
quality['720p'] = 1
if '1080p' in qs:
quality['1080p'] = 1
if 'CAM' in qs or 'TS' in qs:
quality['TS'] = 1
it.quality = '/'.join([ k for k,v in quality.items()])
imdb_url = res['imdb']
if imdb_url != None and len(imdb_url) > 0:
urllist.append("http://www.imdb.com/title/"+ imdb_url)
return it ,urllist
def detail_parse_by_subclass(self,url,page):
it = Item()
it.url = url
con = self.parser.get_parse_data(url,page)
ename = con['name']
if ename!=None and len(ename)>0:
it.ename = ename.split("(")[0].strip()
else:
return None,[]
tlist = []
for t in con['typelist']:
tlist.append(t['type'])
it.type = '/'.join(tlist)
imdbid = url.split("title/")[1].split("/")[0]
if "tt" in imdbid:
imdbid = imdbid.replace('tt','')
it.id = int(imdbid)
##title/tt0061811
it.date = con['date']
#print "imdbname",it.ename
#print "imdbid",it.id
#print "imdb" ,it.type
#print "year",con['date']
it.pic_url = con['pic_url']
if it.pic_url ==None:
it.pic_url="nopic"
it.rate = con['rate']
if it.rate==None:
it.rate=0
it.director = con['director']
it.actors = con['actors']
if it.actors ==None:
return None,[]
it.actors = it.actors.split("|")[0].replace("Stars:",'').strip()
info = con['box']
# Budget: $170,000,000 (estimated)
if "Budget:" in info:
box = info.split("Budget:")[1].split("(estimated)")[0]
box = box.replace(",",'').strip()
p = re.compile(r'([\d]+)')
match = p.search(box)
if match != None:
it.box = int(match.group())/10000
else:
it.box =0
return it,[]
def detail_parse_by_subclass(self,url,page):
res = self.parser.get_parse_data(url,page)
con = res['content']
strlist = con.split("◎")
newurl = []
it = None
if len(strlist)>2:
it = Item()
it.url = url
for s in strlist:
if "译 名" in s:
it.cname = s.split("译 名")[1].strip()
if "片 名" in s:
it.ename = s.split("片 名")[1].strip()
if "年 代" in s:
it.date = s.split("年 代")[1].strip()
if "国 家" in s:
it.location = s.split("国 家")[1].strip()
if "上映时期" in s:
it.date = s.split("上映时期")[1].strip()
elif "上映日期" in s:
it.date = s.split("上映日期")[1].strip()
if "链接" in s:
u = s.split("链接")[1].strip()
if "http://" in u:
pos = u.find("http://")
newurl.append((u[pos:]).strip('/'))
if "导 演" in s:
it.director = s.split("导 演")[1].strip()
if "主 演" in s:
it.actors = s.split("主 演")[1].strip()
elif "演 员" in s:
it.actors = s.split("演 员")[1].strip()
else:
it = Item()
it.url = url
it.content = con
return it ,newurl