- #coding:utf-8
- import requests,xlrd,datetime,threading,sys
- from bs4 import BeautifulSoup
- reload(sys)
- sys.setdefaultencoding("utf-8")
- def beian(url,excel):
- f = xlrd.open_workbook(excel)
- sheet1 = f.sheet_by_name('Sheet1')
- num_cols = sheet1.ncols
- for curr_col in range(num_cols):
- rows = sheet1.col_values(curr_col)
- for each in rows:
- data = {'s': each,'guid': '1e4b4b3f-310f-4aaa-90f7-a552db48758d'}
- r = requests.post(url,data=data)
- soup = BeautifulSoup(r.content,'html.parser')
- tags = soup.find_all('div',id='contenthtml')
- try:
- for tag in tags:
- d_name = tag.find('td',class_='tdright').get_text()
- #print d_name
- print ('%s 已备案') % each
- except AttributeError:
- print ('%s 未备案') % each
- if __name__ == "__main__":
- url = 'http://tool.chinaz.com/beian.aspx'
- excel = (r'C:\\\\1.xlsx')
- threads = []
- print "程序开始运行%s" % datetime.datetime.now()
- t1 = threading.Thread(target=beian,args=(url,excel))
- threads.append(t1)
- for th in threads:
- th.setDaemon(True)
- th.start()
- th.join()
- print "程序结束时间%s" % datetime.datetime.now()
- #beian(url,excel)
- #该片段来自于http://www.codesnippet.cn/detail/0801201614384.html
来源: http://www.codesnippet.cn/detail/0801201614384.html