本文主要分享关于python登录并爬取淘宝信息的相关代码，还是挺不错的，大家可以了解下。
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
|
#!/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 #登录 def login(driver,site): driver.get(site) time.sleep(5) try: #点击请登录 driver.find_element_by_class_name("h").click() time.sleep(5) #输入账号和密码 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) #点击登录 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']") #是否获取到消息,若无则登录 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 #是否成功抓取 if resultstrall !="": f = codecs.open(filename,'w','utf-8') f.write(resultstrall) f.close() #若没有成功抓取将网站写入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) |
小结
有改进策略一起探讨，可以抓取淘宝部分网页内容，根据自己的需求改改吧，会被风控。个人觉得不登录的效果更好。
以上就是本文关于python 登录并爬取淘宝信息代码示例的全部内容，希望对大家有所帮助。感兴趣的朋友可以继续参阅本站其他相关专题。如有不足之处，欢迎留言指出。感谢朋友们对本站的支持！
原文链接：http://blog.csdn.net/Japan__/article/details/50821586
