search = urllib.request.quote(search)

for page in range(1,pagenum+1):
 url = 'http://weixin.sogou.com/weixin?type=2&query='+search+'&page='+str(page)

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()

 import re
  finddata = re.compile('<a target="_blank" href="(.*?)" rel="external nofollow" rel="external nofollow" .*?uigs="article_title_.*?">(.*?)</a>').findall(data)
  #finddata = [('',''),('','')]

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

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

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

 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()

'''
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?type=2&query='+search+'&page='+str(page)
 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()
 import re
 finddata = re.compile('<a target="_blank" href="(.*?)" rel="external nofollow" rel="external nofollow" .*?uigs="article_title_.*?">(.*?)</a>').findall(data)
 #finddata = [('',''),('','')]
 for i in range(len(finddata)):
  title = finddata[i][1]
  title = title.replace('<em><!--red_beg-->','')
  title = title.replace('<!--red_end--></em>','')
  try:
   #标题中可能存在引号
   title = title.replace('“','"')
   title = title.replace('”','"')
  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！')