def getFlesh(self):
try:
for cinemaId in self.cinemas:
cinemaUrl = self.getCinemaUrl(cinemaId)
pageCode = getPageCode(cinemaUrl)
# pattern = re.compile('<p class="cb-tel">.*?([\d].*?)</p>', re.S)
# items = re.findall(pattern, pageCode)
# cinemaTel = items[0].strip()
pattern = re.compile('movieId="(.*?)".*?<img src="(.*?)"', re.S)
items = re.findall(pattern, pageCode)
for item in items:
movieId = item[0]
movieImg = item[1]
if movieId not in self.movies:
self.movies[movieId] = {}
self.movies[movieId]['info'] = {}
self.movies[movieId]['cinemas'] = {}
self.movies[movieId]['info']['img'] = movieImg
self.movies[movieId]['cinemas'][cinemaId] = {}
movieUrl = self.getMovieUrl(cinemaId, movieId)
pageCode = getPageCode(movieUrl)
if 'title' not in self.movies[movieId]['info']:
self.getMovieInfo(pageCode, self.movies[movieId]['info'])
self.moviesIdToTitle[movieId] = self.movies[movieId]['info']['title']
self.moviesTitleToId[self.movies[movieId]['info']['title']] = movieId
self.getMovieCinema(pageCode, self.movies[movieId]['cinemas'][cinemaId])
except urllib.error.URLError as e:
if hasattr(e, 'code'):
print(e.code)
if hasattr(e, 'reason'):
print(e.reason)
return self.movies
def getFlesh(self):
try:
for cinemaId in self.cinemas:
# t = self.cinemasMap[cinemaId];
# url = 'http://bj.meituan.com/shop/'+ t
# pagecode = getPageCode(url)
# pattern = re.compile("class='field-title'>电话：.*?>(.*?)</div>", re.S)
# items = re.findall(pattern, pagecode)
# for item in items:
# cinemaTel = item.strip()
cinemaUrl = self.getCinemaUrl(cinemaId)
pagecode = getPageCode(cinemaUrl)
pattern = re.compile('"cat":(.*?)"id":(.*?),.*?"nm":"(.*?)"', re.S)
items = re.findall(pattern, pagecode)
for item in items:
movieinfo = item[0].strip();
movieId = item[1].strip();
if movieId not in self.movies:
self.movies[movieId] = {}
self.movies[movieId]['cinemas'] = {}
self.movies[movieId]['info'] = {}
self.movies[movieId]['info']['title'] = item[2].strip()
self.moviesIdToTitle[movieId] = self.movies[movieId]['info']['title']
self.moviesTitleToId[self.movies[movieId]['info']['title']] = movieId
self.movies[movieId]['cinemas'][cinemaId] = {}
self.getMovieStatus(movieinfo, self.movies[movieId]['cinemas'][cinemaId])
except urllib.error.URLError as e:
if hasattr(e, 'code'):
print(e.code)
if hasattr(e, 'reason'):
print(e.reason)
def getFlesh(self):
try:
for cinemaId in self.cinemas:
# url = 'https://dianying.taobao.com/cinemaDetail.htm?cinemaId='+cinemaId
# pageCode = getPageCode(url)
# pattern = re.compile('<li>联系电话：(.*?)</li>', re.S)
# items = re.findall(pattern, pageCode)
# for item in items:
# cinemaTel = item.strip()
cinemaUrl = self.getCinemaUrl(cinemaId)
c_pageCode = getPageCode(cinemaUrl)
pattern = re.compile('showId=(.*?)&', re.S)
items = re.findall(pattern, c_pageCode)
items = set(items)
for item in items:
movieId = item
movieUrl = 'http://dianying.taobao.com/cinemaDetailSchedule.htm?cinemaId='+ cinemaId +'&showId='+ movieId
m_pageCode = getPageCode(movieUrl)
if movieId not in self.movies:
self.movies[movieId] = {}
self.movies[movieId]['info'] = {}
self.movies[movieId]['cinemas'] = {}
self.getMovieInfo(m_pageCode, self.movies[movieId]['info'])
self.moviesIdToTitle[movieId] = self.movies[movieId]['info']['title']
self.moviesTitleToId[self.movies[movieId]['info']['title']] = movieId
pattern = re.compile('showId='+movieId+'&showDate=(.*?)&', re.S)
dates = re.findall(pattern, m_pageCode)
dates = set(dates)
self.movies[movieId]['cinemas'][cinemaId] = {}
for date in dates:
url = 'http://dianying.taobao.com/cinemaDetailSchedule.htm?cinemaId='+ cinemaId +'&showId='+ movieId +'&showDate='+date
date = date[5:]
d_pagecode = getPageCode(url)
self.movies[movieId]['cinemas'][cinemaId][date] = {}
self.getMovieStatus(d_pagecode, self.movies[movieId]['cinemas'][cinemaId][date])
except urllib.error.URLError as e:
if hasattr(e, 'code'):
print(e.code)
if hasattr(e, 'reason'):
print(e.reason)
return self.movies
