QQ空间爬取报错问题！

测试积点老人

QQ空间爬取报错：urllib.error.URLError: <urlopen error [WinError 10061] 由于目标计算机积极拒绝，无法连接。>

1. 
   
2. from lxml import etree
   
3. from bs4 import BeautifulSoup
   
4. from selenium import webdriver
   
5. import time
   
6. #使用 selenium
   
7. 
   
8. driver = webdriver.PhantomJS(executable_path="D:\\GHOST/bin/phantomjs.exe")
   
9. driver.maximize_window()
   
10. 
    
11. #登录 QQ 空间
    
12. def get_shuoshuo(qq):
    
13.     driver.get('http://user.qzone.qq.com/{}/311'.format(qq))
    
14.     time.sleep(6.6)
    
15.     try:
    
16.         driver.find_element_by_id('login_div')
    
17.         a = True
    
18.     except:
    
19.         a = False
    
20.     if a == True:
    
21.         driver.switch_to.frame('login_frame')
    
22.         time.sleep(3.3)
    
23.         driver.find_element_by_id('switcher_plogin').click()
    
24.         time.sleep(3.3)
    
25.         driver.find_element_by_id('u').clear()
    
26.         time.sleep(3.3)
    
27.         driver.find_element_by_id('u').send_keys('你的QQ')
    
28.         time.sleep(3.3)
    
29.         driver.find_element_by_id('p').clear()
    
30.         time.sleep(3.3)
    
31.         driver.find_element_by_id('p').send_keys('你的QQ密码')
    
32.         time.sleep(3.3)
    
33.         driver.find_element_by_id('login_button').click()
    
34.         time.sleep(6.6)
    
35. 
    
36. driver.implicitly_wait(3)
    
37. try:
    
38.     driver.find_element_by_id('QM_OwnerInfo_Icon')
    
39.     b = True
    
40. except:
    
41.     b = False
    
42. 
    
43. if b == True:
    
44.     driver.switch_to.frame('app_canvas_frame')
    
45.     content = driver.find_elements_by_css_selector('.content')
    
46.     stime = driver.find_elements_by_css_selector('.c_tx.c_tx3.goDetail')
    
47.     for con,sti in zip(content,stime):
    
48.         data = {
    
49.             'time':sti.text,
    
50.             'shuos':con.text
    
51.         }
    
52.         print(data)
    
53.     pages = driver.page_source
    
54.     soup = BeautifulSoup(pages,'lxml')
    
55. 
    
56. cookie = driver.get_cookies()
    
57. cookie_dict = []
    
58. for c in cookie:
    
59.     ck = "{0}={1};".format(c['name'],c['value'])
    
60.     cookie_dict.append(ck)
    
61. 
    
62. i = ''
    
63. for c in cookie_dict:
    
64.     i += c
    
65. 
    
66. print('Cookies:',i)
    
67. print("================完成================")
    
68. driver.close()
    
69. driver.quit()
    
70. 
    
71. if __name__ == '__main__':
    
72.     get_shuoshuo('目标的QQ号')

复制代码

qqq911

被反爬了

kallinr

反扒

jingzizx

没连上。。。