python3之微信文章爬虫实例讲解

search = urllib.request.quote(search)

for page in range(1,pagenum+1):
 url = 'http://weixin.sogou.com/weixin"htmlcode">

import urllib.request
 header = ('User-Agent','Mozilla/5.0')
 opener = urllib.request.build_opener()
 opener.addheaders = [header]
 urllib.request.install_opener(opener)
 data = urllib.request.urlopen(url).read().decode()


得到页面内容，采用正则表达获取相关数据


 import re
  finddata = re.compile('<a target="_blank" href="(.*" rel="external nofollow" rel="external nofollow" .*"article_title_.*">(.*"htmlcode">

 title = title.replace('<em><!--red_beg-->','')
 title = title.replace('<!--red_end--></em>','')
 link = link.replace('amp;','')


将处理后的标题和链接保存在列表中


 title_link.append(link)
 title_link.append(title)


如此搜索的标题和链接都得到了，接下来导入Excel
先创建Excel


 import xlsxwriter
 workbook = xlsxwriter.Workbook(search+'.xlsx')
 worksheet = workbook.add_worksheet('微信')


将title_link中的数据导入Excel


 for i in range(0,len(title_link),2):
  worksheet.write('A'+str(i+1),title_link[i+1])
  worksheet.write('C'+str(i+1),title_link[i])
 workbook.close()


完整代码：


'''
python3.4 + windows
羽凡-2017/7/11-
用于搜索微信文章，保存标题及链接至Excel中
每个页面10秒延迟，防止被限制
import urllib.request,xlsxwriter,re,time
'''
import urllib.request
search = str(input("搜索微信文章："))
pagenum = int(input('搜索页数:'))
import xlsxwriter
workbook = xlsxwriter.Workbook(search+'.xlsx')
search = urllib.request.quote(search)
title_link = []
for page in range(1,pagenum+1):
 url = 'http://weixin.sogou.com/weixin"_blank" href="(.*" rel="external nofollow" rel="external nofollow" .*"article_title_.*">(.*"')
   title = title.replace('&rdquo;','"')
  except:
   pass
  link = finddata[i][0]
  link = link.replace('amp;','')
  title_link.append(link)
  title_link.append(title)
 print('第'+str(page)+'页')
 import time
 time.sleep(10)
worksheet = workbook.add_worksheet('微信')
worksheet.set_column('A:A',70)
worksheet.set_column('C:C',100)
bold = workbook.add_format({'bold':True})
worksheet.write('A1','标题',bold)
worksheet.write('C1','链接',bold)
for i in range(0,len(title_link),2):
 worksheet.write('A'+str(i+1),title_link[i+1])
 worksheet.write('C'+str(i+1),title_link[i])
workbook.close()
print('导入Excel完毕！')


以上这篇python3之微信文章爬虫实例讲解就是小编分享给大家的全部内容了，希望能给大家一个参考，也希望大家多多支持。