Python爬虫: 用urllib2+beautifulsoup写的抓取网页内容的示例

BeautifulSoup是一个可以解析HTML或XML内容的python库，和java的Dom4j有点类似。当用urllib2抓取到网页的HTML源码之后，调用beautifulSoup的API就可以解析HTML,比用自己写正则表达式简单高效得多。

安装BeautifulSoup: sudo apt-get install python-bs4   (注意是：python-bs4 )

检查是否安装成功: from bs4 import BeautifulSoup

代码:

# coding=utf-8
import urllib2
import re
import os
import sys
from bs4 import BeautifulSoup

#解决中文输出乱码问题，write(中文)时需要将中文unicode。 write(unicode('中文'))
reload(sys)
sys.setdefaultencoding('utf-8')

class Spider:
	'''
		这是一个简单的用于抓取'晚安心语'里的语句
		晚安心语的链接: http://www.vikilife.com/tag/晚安心语
	'''
	def __init__(self):
		self.url='http://www.vikilife.com/tag/%E6%99%9A%E5%AE%89%E5%BF%83%E8%AF%AD/page/'

	
	def load_url(self,pageNum):
		'''
			Send HTTP request to the special URL and get some useful information
		
		'''
		current_url= self.url + str(pageNum)
		user_agent='Mozilla/5.0 (Windows NT 6.1; WOW64; rv:34.0) Gecko/20100101 Firefox/34.0'
		headers={'User-Agent':user_agent}
		
		#Send Http Request to URL 
		req = urllib2.Request(current_url,headers=headers)
		response = urllib2.urlopen(req)

		#Read HTML response
		html = response.read()
		
		#Get some useful information from the HTML
		#pattern = re.compile(r'<h2>.*?title="(.*?)"',re.S)
		#result_list = pattern.findall(html)
		result_list = self.analysis_html(html)

		#out put result list
		#print result_list

		#write result to log file
		self.write_result_log(result_list,pageNum)

	def analysis_html(self,html):
		'''
			Use BeautifulSoup to analysis HTML
		'''

		#create BeautifulSoup Object
		soup = BeautifulSoup(html)

		#format out put
		#print soup.prettify()

		print soup.title

		result_list = []

		for link in soup.find_all("div","indexs"):
			title= link.find('a').text
			result_list.append(title)

		return result_list




	def write_result_log(self,result_list,pageNum):
		'''
			write result list to log file
		'''
	
		filePath= os.getcwd() + '/log/wananxinyu_'+str(pageNum)+'.log'
		
		file=open(filePath,'w')
		for result in result_list:
			file.write(unicode(result))
			file.write("\n")
		file.close()
		


if __name__=='__main__':
	spider=Spider()
	for pageNum in range(1,10):
		spider.load_url(pageNum)