使用BeautifulSoup爬虫程序获取百度搜索结果的标题和url示例
本文导语: 熟悉Java的jsoup包的话,对于Python的BeautifulSoup库应该很容易上手。 代码如下:#coding: utf-8import sysimport urllibimport urllib2from BeautifulSoup import BeautifulSoup question_word = "吃货 程序员"url = "http://www.baidu.com/s?wd=" + urllib.quote(question_word.decode(s...
熟悉Java的jsoup包的话,对于Python的BeautifulSoup库应该很容易上手。
#coding: utf-8
import sys
import urllib
import urllib2
from BeautifulSoup import BeautifulSoup
question_word = "吃货 程序员"
url = "http://www.baidu.com/s?wd=" + urllib.quote(question_word.decode(sys.stdin.encoding).encode('gbk'))
htmlpage = urllib2.urlopen(url).read()
soup = BeautifulSoup(htmlpage)
print len(soup.findAll("table", {"class": "result"}))
for result_table in soup.findAll("table", {"class": "result"}):
a_click = result_table.find("a")
print "-----标题----n" + a_click.renderContents()#标题
print "----链接----n" + str(a_click.get("href"))#链接
print "----描述----n" + result_table.find("div", {"class": "c-abstract"}).renderContents()#描述
print