python+bs4+urllib

# -*- coding: utf-8 -*-
# 
# 
# 
from bs4 import BeautifulSoup
import urllib2
import sys
reload(sys)
sys.setdefaultencoding('utf-8')
###url = 'https://www.qidian.com/search?kw=%E7%AC%91%E5%82%B2%E6%B1%9F%E6%B9%96'
#
#
#
class main():
    def __init__(self):
        pass
    def search(self):
        '''查询函数'''
        ####输入关键字
        ####访问url，获取信息
        ####存储信息
        print '-'*80
        #print '--开始输入关键字: '.decode('utf-8').encode('gbk')
        #key = raw_input('key: ')
        key = urllib2.quote('笑傲江湖')
        url = 'https://www.qidian.com/search?kw='+key
        print '访问的网址是--'.decode('utf-8').encode('gbk')+url
        #####开始访问
        self.spider(url)
    def spider(self, url):
        print '-'*80
        print '开始访问网页'.decode('utf-8').encode('gbk')
        print '-'*80
        response = urllib2.urlopen(url).read()
        obj = BeautifulSoup(response,'html.parser')
        div_list = obj.find('div',{'class':'book-img-text'}).find_all('li')
        for v in div_list:
            name =  v.find('h4').find('a').text
            intro = v.find('div',{'class':'book-mid-info'}).find('p',{'class':'intro'}).text
            print intro
            
    def test(self):
        print urllib2.quote('笑傲江湖')


if __name__ == '__main__':
    book = main()
    book.search()

 

转载于:https://www.cnblogs.com/shuangzikun/p/taotao_python_bs4_urllib.html