0 条评论

1、使用工具:
Python3.5
BeautifulSoup
2、抓取网站：
csdn首页文章列表 http://blog.csdn.net/
3、分析网站文章列表代码：

4、实现抓取代码：

__author__ = 'Administrator'
import urllib.request
import re
from bs4 import BeautifulSoup


########################################################
#
#              抓取csdn首页文章http://blog.csdn.net/?&page=1
#
#             参数baseUrl是要访问的网站地址
#
########################################################
class CsdnUtils(object):
    def __init__(self):
        user_agent='Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/50.0.2661.102 Safari/537.36'
        self.headers ={'Cache-Control':'max-age=0',
                        'Connection':'keep-alive',
                        'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
                        'User-Agent':user_agent,
                        }
        self.contentAll=set()
    def getPage(self,url=None):
        request=urllib.request.Request(url,headers=self.headers)
        response=urllib.request.urlopen(request)
        soup=BeautifulSoup(response.read(),"html.parser")
        #print(soup.prettify())
        return soup
    def parsePage(self,url=None,page_num=None):
        soup=self.getPage(url)
        itemBlog=soup.find_all('dl','blog_list clearfix')
        cnArticle=CsdnUtils
        print("========================第",page_num,"页======================================")
        for i,itemSingle in enumerate(itemBlog):
            cnArticle.num=i
            cnArticle.author=itemSingle.find('a','nickname').string
            cnArticle.postTime=itemSingle.find('label').string
            cnArticle.articleView=itemSingle.find('em').string
            cnArticle.title=itemSingle.find('h3',"tracking-ad").string
            cnArticle.url=itemSingle.find("h3").find("a").get("href")
            print("数据：",cnArticle.num+1,'t',cnArticle.author,'t',cnArticle.postTime,'t',cnArticle.articleView,'t',cnArticle.title,'t',cnArticle.url)


#######     执行    ########
if __name__ =="__main__":

    #要抓取的网页地址'http://blog.csdn.net/?&page={}'.format(i+1),i+1)
    url = "http://blog.csdn.net"

    cnblog=CsdnUtils()
    for i in range(0,2):
        cnblog.parsePage(url,i+1)

5、执行结果：