Python爬豆瓣电影实例

#!/usr/bin/python# -*- coding: UTF-8 -*-import urllib2class HtmlDownloader(object):  def downlod(self, url):    if url is None:      return None    response = urllib2.urlopen(url)    if response.getcode() != 200:      return None    return response.read()

#!/usr/bin/python# -*- coding: UTF-8 -*-class HtmlOutputer(object):  def collect_data(self, movie_data):    if movie_data is None:      return    fout = open('output.html', 'a+')    for data in movie_data:      print data['name'] + '|', data['rate'] + '|', data['actor'], '/n'      fout.write('%s,' % data['name'].encode('utf-8'))      fout.write('%s,' % data['rate'])      fout.write('%s/n' % data['actor'].encode('utf-8'))    fout.close()

#!/usr/bin/python# -*- coding: UTF-8 -*-from bs4 import BeautifulSoupclass HtmlParser(object):  def __init__(self):    pass  def parser_html(self, cnt):    if cnt is None:      return    soup = BeautifulSoup(cnt, 'html.parser', from_encoding='utf-8')    # movie_name, movie_desc, movie_rate =    return self.get_movie_names(soup)  def get_movie_names(self, soup):    movie_data = []    movie_all = soup.find('div', class_='article').find_next('table').find_next_sibling('div').find_next_sibling('div').find_all('table')    count = 1    for movie_one in movie_all:      movie_data.append(self.get_movie_name(movie_one))      # if count > 2:      #   break      count += 1    return movie_data  def get_movie_name(self, cnt):    info = {}    soup = BeautifulSoup(str(cnt), 'html.parser', from_encoding='utf-8')    movie_one = soup.find('tr', class_='item').find_next('td').find_next_sibling('td').find('div', class_='pl2')    info['name'] = movie_one.find('a').get_text().replace("/n", "").replace(" ", "")    info['actor'] = movie_one.find('p', class_='pl').get_text().replace("/n", "").replace(" ", "")    info['rate'] = movie_one.find('div', class_='star clearfix').find('span', class_='rating_nums').get_text()    return info

#!/usr/bin/python# -*- coding: UTF-8 -*-import html_parser, html_outputer, html_downloaderclass SpiderMain(object):  def __init__(self):    self.parser = html_parser.HtmlParser()    self.outputer = html_outputer.HtmlOutputer()    self.downloader = html_downloader.HtmlDownloader()  def craw(self, url):    html_cnt = self.downloader.downlod(url)    movie_data = self.parser.parser_html(html_cnt)    self.outputer.collect_data(movie_data)if __name__ == '__main__':  url = 'https://movie.douban.com/tag/2017?start=100&type=T'  spider = SpiderMain()  spider.craw(url)