Python2.7结合selenium抓取百度失信人员信息

python代码如下:

# -*- coding:utf-8*-
from selenium import webdriver
from selenium.webdriver import ActionChains
import time
import re
import sys

#chromedriver.exe存放的路径要写对
driver = webdriver.Chrome("D:\Python27\chromedriver.exe")

def BiduShixinClick():
 
  url = "https://www.baidu.com/s?ie=utf-8&f=8&rsv_bp=0&rsv_idx=1&tn=baidu&wd=%E5%A4%B1%E4%BF%A1&rsv_pq=cee6b7640002853a&rsv_t=12e94n%2Fq7el%2FvBVJpTxG5Pnv2mUUzKylUH3Xersp1qqCquo4zGZW0ozpBro&rqlang=cn&rsv_enter=0&rsv_sug3=4&rsv_sug1=4&rsv_sug7=100&inputT=6783&rsv_sug4=7163"
  driver.get(url)
  f=open('F:/data.txt','a')
  #driver.execute_script(actions)
  for i in range(1,100): 
    time.sleep(2)
    strNames = driver.find_elements_by_class_name("op_trust_name")
    strCards = driver.find_elements_by_class_name("op_trust_papers")
    for i in range(0,len(strNames)):
      print strNames[i].text + "-" + strCards[i].text
      f.write(strNames[i].text +","+strCards[i].text+"\r\n")

    strclicks = driver.find_element_by_class_name("op_trust_page_next")
    print i   
    strclicks.click()        
  f.flush
  f.close
  driver.quit()

if __name__ == '__main__':
  reload(sys)
  sys.setdefaultencoding('utf-8')
  BiduShixinClick()

猜你喜欢

转载自blog.csdn.net/tiandiqing/article/details/84819083