[已解决]关于爬虫的问题

Mr丶张

最近学了一点爬虫但是不知道这个为什么这个程序一直报错

1. import urllib.request
   
2. from lxml import etree
   
3. 
   
4. def create_response(page):
   
5.     if 1 == page:
   
6.         url = 'https://sc.chinaz.com/tu/meinv.html'
   
7.     else:
   
8.         str(page)
   
9.         url = "https://sc.chinaz.com/tu/meinv-%s-0-0.html"%page
   
10. 
    
11.     headers = {
    
12.         "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/102.0.0.0 Safari/537.36"
    
13.     }
    
14. 
    
15.     response = urllib.request.Request(url, headers = headers)
    
16. 
    
17.     return response
    
18. 
    
19. def get_info(response):
    
20.     request = urllib.request.urlopen(response)
    
21.     content = request.read().decode('utf-8')
    
22. 
    
23.     return content
    
24. 
    
25. def down_img(content):
    
26.     tree = etree.HTML(content)
    
27.     nameList = tree.xpath('//div[@id="ulcontent"]//div//img/@alt')
    
28.     imgList = tree.xpath('//div[@id="ulcontent"]//div//img/@data-src')
    
29. 
    
30.     for i in range(len(nameList) - 1):
    
31.         img = 'https:' + imgList[i]
    
32.         name = nameList[i]
    
33.         print(img)
    
34.         # urllib.request.urlretrieve(img, name + '.jpg')
    
35.     print("Over")
    
36. 
    
37. if __name__ == '__main__':
    
38.     startPage = int(input("请输入开始页:"))
    
39.     endPage = int(input("请输入结束页:"))
    
40. 
    
41.     for page in range(startPage, endPage + 1):
    
42.         response = create_response(page)
    
43.         content = get_info(response)
    
44.         down_img(content)
    
45. 
    

复制代码

最佳答案

月排行榜 / 总排行榜

临时号

2022-6-12 00:47:19

Mr丶张 发表于 2022-6-12 00:21
34行的注释解开了会报错

注意:你的网址中有\,应当全部替换为/

1. import urllib.request
   
2. from lxml import etree
   
3. 
   
4. def create_response(page):
   
5.     if 1 == page:
   
6.         url = 'https://sc.chinaz.com/tu/meinv.html'
   
7.     else:
   
8.         str(page)
   
9.         url = "https://sc.chinaz.com/tu/meinv-%s-0-0.html"%page
   
10. 
    
11.     headers = {
    
12.         "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/102.0.0.0 Safari/537.36"
    
13.     }
    
14. 
    
15.     response = urllib.request.Request(url, headers = headers)
    
16. 
    
17.     return response
    
18. 
    
19. def get_info(response):
    
20.     request = urllib.request.urlopen(response)
    
21.     content = request.read().decode('utf-8')
    
22. 
    
23.     return content
    
24. 
    
25. def down_img(content):
    
26.     tree = etree.HTML(content)
    
27.     nameList = tree.xpath('//div[@id="ulcontent"]//div//img/@alt')
    
28.     imgList = tree.xpath('//div[@id="ulcontent"]//div//img/@data-src')
    
29. 
    
30.     for i in range(len(nameList) - 1):
    
31.         img = 'https:' + imgList[i]
    
32.         name = nameList[i]
    
33.         print(img)
    
34.         urllib.request.urlretrieve(img.replace("\","/"), name + '.jpg')  # 注意:你的网址中有\,应当全部替换为/
    
35.     print("Over")
    
36. 
    
37. if __name__ == '__main__':
    
38.     startPage = int(input("请输入开始页:"))
    
39.     endPage = int(input("请输入结束页:"))
    
40. 
    
41.     for page in range(startPage, endPage + 1):
    
42.         response = create_response(page)
    
43.         content = get_info(response)
    
44.         down_img(content)

复制代码

跳转到最佳答案楼层

Mr丶张

34行的注释解开了会报错

临时号

我运行一切正常啊

临时号

Mr丶张 发表于 2022-6-12 00:21
34行的注释解开了会报错

注意:你的网址中有\,应当全部替换为/

1. import urllib.request
   
2. from lxml import etree
   
3. 
   
4. def create_response(page):
   
5.     if 1 == page:
   
6.         url = 'https://sc.chinaz.com/tu/meinv.html'
   
7.     else:
   
8.         str(page)
   
9.         url = "https://sc.chinaz.com/tu/meinv-%s-0-0.html"%page
   
10. 
    
11.     headers = {
    
12.         "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/102.0.0.0 Safari/537.36"
    
13.     }
    
14. 
    
15.     response = urllib.request.Request(url, headers = headers)
    
16. 
    
17.     return response
    
18. 
    
19. def get_info(response):
    
20.     request = urllib.request.urlopen(response)
    
21.     content = request.read().decode('utf-8')
    
22. 
    
23.     return content
    
24. 
    
25. def down_img(content):
    
26.     tree = etree.HTML(content)
    
27.     nameList = tree.xpath('//div[@id="ulcontent"]//div//img/@alt')
    
28.     imgList = tree.xpath('//div[@id="ulcontent"]//div//img/@data-src')
    
29. 
    
30.     for i in range(len(nameList) - 1):
    
31.         img = 'https:' + imgList[i]
    
32.         name = nameList[i]
    
33.         print(img)
    
34.         urllib.request.urlretrieve(img.replace("\","/"), name + '.jpg')  # 注意:你的网址中有\,应当全部替换为/
    
35.     print("Over")
    
36. 
    
37. if __name__ == '__main__':
    
38.     startPage = int(input("请输入开始页:"))
    
39.     endPage = int(input("请输入结束页:"))
    
40. 
    
41.     for page in range(startPage, endPage + 1):
    
42.         response = create_response(page)
    
43.         content = get_info(response)
    
44.         down_img(content)

复制代码

临时号

Mr丶张 发表于 2022-6-12 00:21
34行的注释解开了会报错

问题解决了吗?