def getWantToSeeMovies(self):
searchURL = self.baseURL + '/usuario/' + self.username + '/quero-ver/'
moviesVec = []
netflixVec = []
nThreads = 8
threadPool = ThreadPool(nThreads)
threadPool.startWorking()
def parsePage(pageUrl):
wantToSeeCatalogueHTML = urllib.request.urlopen(
urllib.request.Request(pageUrl, headers=self.hdr))
catalogueSoup = BeautifulSoup(wantToSeeCatalogueHTML,
'html.parser')
print(pageUrl)
#looping through each movie in the current page
for movieDiv in catalogueSoup.findAll(
'li', {'class': 'span2 movie_list_item'}):
divSoup = BeautifulSoup(str(movieDiv), 'html.parser')
moviehref = str(divSoup.find("a")['href'])
print(moviehref)
movieURL = self.baseURL + moviehref
threadPool.putInQueue(parseMovie, {"movieURL": movieURL})
def parseMovie(movieURL):
movie = {}
moviePageHtml = urllib.request.urlopen(
urllib.request.Request(movieURL, headers=self.hdr))
moviePageSoup = BeautifulSoup(moviePageHtml, 'html.parser')
movie['name'] = str(
moviePageSoup.find('h2', {
'class': 'movie-original-title'
}).string)
movie['duration'] = str(
moviePageSoup.find('span', {
'class': 'running_time'
}).string)
print(movie)
moviesVec.append(movie)
threadPool.putInQueue(checkNetflix, {'title': movie['name']})
def checkNetflix(title):
netflixWrapper = NetflixWrapper()
resp = netflixWrapper.isTitleInNetflix(title)
if (resp[0]):
netflixVec.append(resp[1])
for i in range(1, self.getWantToSeePages() + 1):
pageUrl = searchURL + '?pagina=' + str(i)
threadPool.putInQueue(parsePage, {'pageUrl': pageUrl})
#block until all tasks are done
threadPool.end()
return [moviesVec, netflixVec]
def getWantToSeeMovies(self):
searchURL = self.baseURL + '/usuario/' + self.username + '/quero-ver/';
moviesVec = []
netflixVec = []
nThreads = 8
threadPool = ThreadPool(nThreads)
threadPool.startWorking()
def parsePage(pageUrl):
wantToSeeCatalogueHTML = urllib.request.urlopen(urllib.request.Request(pageUrl, headers=self.hdr))
catalogueSoup = BeautifulSoup(wantToSeeCatalogueHTML, 'html.parser')
print(pageUrl)
#looping through each movie in the current page
for movieDiv in catalogueSoup.findAll('li', { 'class': 'span2 movie_list_item'}):
divSoup = BeautifulSoup(str(movieDiv), 'html.parser')
moviehref = str(divSoup.find("a")['href'])
print(moviehref)
movieURL = self.baseURL + moviehref
threadPool.putInQueue(parseMovie, {"movieURL": movieURL})
def parseMovie(movieURL):
movie = {}
moviePageHtml = urllib.request.urlopen(urllib.request.Request(movieURL, headers=self.hdr))
moviePageSoup = BeautifulSoup(moviePageHtml, 'html.parser')
movie['name'] = str(moviePageSoup.find('h2',{'class':'movie-original-title'}).string)
movie['duration'] = str(moviePageSoup.find('span',{'class':'running_time'}).string)
print(movie)
moviesVec.append(movie)
threadPool.putInQueue(checkNetflix, {'title': movie['name']})
def checkNetflix(title):
netflixWrapper = NetflixWrapper()
resp = netflixWrapper.isTitleInNetflix(title)
if(resp[0]):
netflixVec.append(resp[1])
for i in range(1, self.getWantToSeePages() + 1):
pageUrl = searchURL + '?pagina=' + str(i)
threadPool.putInQueue(parsePage, {'pageUrl': pageUrl})
#block until all tasks are done
threadPool.end()
return [moviesVec, netflixVec]
