Python爬虫包BeautifulSoup学习实例（五）

本文为大家分享了Python爬虫包BeautifulSoup学习实例，具体内容如下

BeautifulSoup

使用BeautifulSoup抓取豆瓣电影的一些信息。

# -*- coding: utf-8 -*-# @Author: HaonanWu# @Date:  2016-12-24 16:18:01# @Last Modified by:  HaonanWu# @Last Modified time: 2016-12-24 17:25:33import urllib2import jsonfrom bs4 import BeautifulSoupdef nowplaying_movies(url):  user_agent = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36'  headers = {'User-Agent':user_agent}  request = urllib2.Request(url = url, headers = headers)  response = urllib2.urlopen(request)  soup_packetpage = BeautifulSoup(response, 'lxml')  items = soup_packetpage.findAll("li", class_="list-item")  # items = soup_packetpage.findAll("li", {"class" : "list-item"}) 等价写法  movies = []  for item in items:    if item.attrs['data-category'] == 'nowplaying':      movie = {}      movie['title'] = item.attrs['data-title']      movie['score'] = item.attrs['data-score']      movie['director'] = item.attrs['data-director']      movie['actors'] = item.attrs['data-actors']      movies.append(movie)      print('%(title)s|%(score)s|%(director)s|%(actors)s' % movie)  return moviesif __name__ == '__main__':  url = 'https://movie.douban.com/nowplaying/beijing/'  movies = nowplaying_movies(url)  print('%s' % json.dumps(movies, sort_keys=True, indent=4, separators=(',', ': ')))

HTMLParser

使用HTMLParser实现上述功能

这里有一些HTMLParser的基础教程

由于HtmlParser自2006年以后就再没更新，目前很多人推荐使用jsoup代替它。

# -*- coding: utf-8 -*-# @Author: HaonanWu# @Date:  2016-12-24 15:57:54# @Last Modified by:  HaonanWu# @Last Modified time: 2016-12-24 17:03:27from HTMLParser import HTMLParserimport urllib2import jsonclass MovieParser(HTMLParser):  def __init__(self):    HTMLParser.__init__(self)    self.movies = []  def handle_starttag(self, tag, attrs):    def _attr(attrlist, attrname):      for attr in attrlist:        if attr[0] == attrname:          return attr[1]      return None    if tag == 'li' and _attr(attrs, 'data-title') and _attr(attrs, 'data-category') == 'nowplaying':      movie = {}      movie['title'] = _attr(attrs, 'data-title')      movie['score'] = _attr(attrs, 'data-score')      movie['director'] = _attr(attrs, 'data-director')      movie['actors'] = _attr(attrs, 'data-actors')      self.movies.append(movie)      print('%(title)s|%(score)s|%(director)s|%(actors)s' % movie)def nowplaying_movies(url):  headers = {'User-Agent' : 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.99 Safari/537.36'}    req = urllib2.Request(url, headers=headers)  s = urllib2.urlopen(req)  parser = MovieParser()  parser.feed(s.read())  s.close()  return parser.moviesif __name__ == '__main__':  url = 'https://movie.douban.com/nowplaying/beijing/'  movies = nowplaying_movies(url)  print('%s' % json.dumps(movies, sort_keys=True, indent=4, separators=(',', ': ')))