[已解决]求助大神xpath取值返回值为空的问题

zouyin

本人是新手，刚学习python爬虫，想试试水，然后就想试试爬取好看视频，由于是动态网站，在nrtwork里面用正则爬取到了视频链接，并且下载下来，后来发现爬取的并不是超清的链接，后来就换了一个思路，先从门户网站提取单个视频的链接，在依次请求单个视频网站，在用xpath提取html中的超清链接，可是就是无法返回正确的值。所以想问下大神，这个问题怎么解决，再次声明，我想爬取的是超清的链接，而不是标清的直接用正则匹配出来的！
下面是我的代码，新手刚学，代码写的很乱，见谅

import requests
import json
from lxml import etree


url ="https://haokan.baidu.com/videoui/api/videorec?tab=yingshi&act=pcFeed&pd=pc&num=5&shuaxin_id=1583468488484"

headers = {
        "user-agent": "Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko",
        "cookie": "BIDUPSID=46B223B8A7EAECCA159168C5EF538730; PSTM=1580279175; BAIDUID=46B223B8A7EAECCA1D299D6661AB1F78:FG=1; BDUSS=wyaHJzcUFsOWdtYkVMQ0FneWFCfjVUOTcyTXZMRHJmUWJtbWlrOW1abW1zbGhlSVFBQUFBJCQAAAAAAAAAAAEAAAC9Y9sXYTE1Mzg4NjU0AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAKYlMV6mJTFeY0; Hm_lvt_4aadd610dfd2f5972f1efee2653a2bc5=1581861785,1581914947,1582809107; COMMON_LID=8d29357345ecabe02bcad89b3bd55ab6; reptileData=%7B%22data%22%3A%227e946299daa801da748c32b90adc9d7587f263b748089c6f531c52f9288451033df59d8bcd2c41c5ea90515a8a59833e572833311e74af94f7e2aa1794a63686198f2e47c079610fbaf9740df8731397ca5a287539edecd7194117534d906ad3d67750c2ddd9d756c1352c874ec21387f39c3f33f49f4f9d63f2d0f530ed45645ab8b1fe1841446ca7f3e2bdc2badd48%22%2C%22key_id%22%3A%2230%22%2C%22sign%22%3A%22b3439eb1%22%7D; PC_TAB_LOG=haokan_website_page; Hm_lpvt_4aadd610dfd2f5972f1efee2653a2bc5=1582809193"
}
response = requests.get(url,headers=headers)
data = response.text
#print(data)
json_data = json.loads(data)
#print(json_data)
date_list = json_data['data']['response']['videos']
#print(date_list)
urls = []
for date in date_list:
    video_urls = date['url']
    #print(video_urls)
    urls.append(date['url'])
#print(urls)

for url_video in urls:
    responses = requests.get(url_video,headers=headers)
    data_res = responses.text
    html_ele = etree.HTML(data_res)
    url_video = html_ele.xpath('/html/body/div/div/div[1]/div[1]/div/hk-controls/hk-definition/ul/li[3]')
    print(url_video)

最佳答案

月排行榜 / 总排行榜

wp231957

2020-3-9 06:26:13

https://fishc.com.cn/forum.php?m ... &extra=page%3D4

跳转到最佳答案楼层

zouyin

1. import requests
   
2. import json
   
3. from lxml import etree
   
4. 
   
5. 
   
6. url ="https://haokan.baidu.com/videoui/api/videorec?tab=yingshi&act=pcFeed&pd=pc&num=5&shuaxin_id=1583468488484"
   
7. 
   
8. headers = {
   
9.         "user-agent": "Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; rv:11.0) like Gecko",
   
10.         "cookie": "BIDUPSID=46B223B8A7EAECCA159168C5EF538730; PSTM=1580279175; BAIDUID=46B223B8A7EAECCA1D299D6661AB1F78:FG=1; BDUSS=wyaHJzcUFsOWdtYkVMQ0FneWFCfjVUOTcyTXZMRHJmUWJtbWlrOW1abW1zbGhlSVFBQUFBJCQAAAAAAAAAAAEAAAC9Y9sXYTE1Mzg4NjU0AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAKYlMV6mJTFeY0; Hm_lvt_4aadd610dfd2f5972f1efee2653a2bc5=1581861785,1581914947,1582809107; COMMON_LID=8d29357345ecabe02bcad89b3bd55ab6; reptileData=%7B%22data%22%3A%227e946299daa801da748c32b90adc9d7587f263b748089c6f531c52f9288451033df59d8bcd2c41c5ea90515a8a59833e572833311e74af94f7e2aa1794a63686198f2e47c079610fbaf9740df8731397ca5a287539edecd7194117534d906ad3d67750c2ddd9d756c1352c874ec21387f39c3f33f49f4f9d63f2d0f530ed45645ab8b1fe1841446ca7f3e2bdc2badd48%22%2C%22key_id%22%3A%2230%22%2C%22sign%22%3A%22b3439eb1%22%7D; PC_TAB_LOG=haokan_website_page; Hm_lpvt_4aadd610dfd2f5972f1efee2653a2bc5=1582809193"
    
11. }
    
12. response = requests.get(url,headers=headers)
    
13. data = response.text
    
14. #print(data)
    
15. json_data = json.loads(data)
    
16. #print(json_data)
    
17. date_list = json_data['data']['response']['videos']
    
18. #print(date_list)
    
19. urls = []
    
20. for date in date_list:
    
21.     video_urls = date['url']
    
22.     #print(video_urls)
    
23.     urls.append(date['url'])
    
24. #print(urls)
    
25. 
    
26. for url_video in urls:
    
27.     responses = requests.get(url_video,headers=headers)
    
28.     data_res = responses.text
    
29.     html_ele = etree.HTML(data_res)
    
30.     url_video = html_ele.xpath('/html/body/div/div/div[1]/div[1]/div/hk-controls/hk-definition/ul/li[3]')
    
31.     print(url_video)

复制代码

wp231957

用selenium

wp231957

https://fishc.com.cn/forum.php?m ... &extra=page%3D4

zouyin

wp231957 发表于 2020-3-9 06:26
https://fishc.com.cn/forum.php?mod=viewthread&tid=159724&extra=page%3D4

感谢给思路