python login and crawl taobao information code example

This article mainly shares the relevant code about python login and crawls taobao information, which is quite good, you can understand.

#!/usr/bin/env python 
# -*- coding:utf-8 -*- 
from selenium import webdriver 
import time 
import datetime 
import traceback 
import logging 
import os 
from selenium.webdriver.common.action_chains import ActionChains 
import codecs 
# The login  
def login(driver,site): 
 driver.get(site) 
 time.sleep(5) 
 try: 
  # Click to login  
  driver.find_element_by_class_name("h").click() 
  time.sleep(5) 
  # Enter your account number and password  
  driver.find_element_by_id("TPL_username_1").send_keys(u"yourusername") 
  time.sleep(5) 
  #print driver.find_element_by_id("TPL_username_1") 
  driver.find_element_by_id("TPL_password_1").send_keys(u"yourpsd") 
  time.sleep(5) 
 
  # Click login  
  driver.find_element_by_id("J_SubmitStatic").click() 
  time.sleep(30) 
 except: 
  print u"failure" 
def crawlmarket(driver,filename,site): 
 #driver = webdriver.Firefox() 
 driver.get(site) 
 driver.maximize_window() 
 time.sleep(10) 
 driver.refresh() 
 time.sleep(10) 
 test = driver.find_elements_by_xpath("//a[@class='J_ItemLink']") 
 # Whether the message was retrieved , If not, log in  
 if len(test)==0: 
  login(driver,site) 
 time.sleep(30) 
 resultstrall="" 
 resultstr="" 
 strinfo ="" 
 for i in range(0,len(test),1): 
  if test[i].text != "" : 
   resultstr = test[i].text.strip()+'\n' 
   print resultstr 
   resultstrall += resultstr 
 # Whether the grab is successful  
 if resultstrall !="": 
  f = codecs.open(filename,'w','utf-8') 
  f.write(resultstrall) 
  f.close() 
 # If it does not crawl to write to the site error 
 else: 
  strinfo = filename+","+site 
  print strinfo 
  ferror = codecs.open("error.txt",'a','utf-8') 
  ferror.write(strinfo) 
  ferror.close() 
 driver.quit() 

def crawltaobaosousuo(driver,filename,site): 
 #driver = webdriver.Firefox() 
 driver.get(site) 
 driver.maximize_window() 
 time.sleep(10) 
 driver.get(site) 
 time.sleep(30) 
 driver.refresh() 
 test = driver.find_elements_by_xpath("//a[@class='J_ClickStat']") 
 resultstrall="" 
 resultstr="" 
 strinfo ="" 
 for i in range(0,len(test),1): 
  if test[i].text != "" : 
   resultstr = test[i].text.strip()+'\n' 
   print resultstr 
   resultstrall += resultstr 
 if resultstrall !="": 
  f = codecs.open(filename,'w','utf-8') 
  f.write(resultstrall) 
  f.close() 
 else: 
  strinfo = filename+","+site 
  print strinfo 
  ferror = codecs.open("error.txt",'a','utf-8') 
  ferror.write(strinfo) 
  ferror.close() 
 driver.quit() 
def jiexi(driver): 
 f = open("1.txt","r") 
 for line in f: 
  time.sleep(60) 
  info = line.split(",") 
  href = info[1] 
  filename = info[0].decode("utf-8") 
  print filename 
  if "markets" in href: 
   crawlmarket(driver,filename,href) 
  else: 
   crawltaobaosousuo(driver,filename,href) 
if __name__ =='__main__': 
 driver = webdriver.Firefox() 
 jiexi(driver) 

summary

There is an improvement strategy 1 to discuss, you can grab part of taobao web page content, according to their own needs to change, will be risk control. Personally, I think it's better not to log in.

The above is the entire content of this article on python login and crawl Taobao information code example, hope to help you. Those who are interested can continue to see other related topics on this site. If there is any deficiency, please let me know. Thank you for your support!