这个站资料能扒不

xia

比如这个页面
http://read.nlc.cn/OutOpenBook/OpenObjectBook?aid=403&bid=17912.0

huaheshang

多少预算

skd363

爬这个站？茶好喝

cowe

huaheshang 发表于 2021-12-15 12:45
多少预算

我猜楼主问的应该是 扒这个网站的内容 刑不刑，            

miven

1. import requests
   
2. import re
   
3. 
   
4. def get_filename_from_cd(cd):
   
5.     """
   
6.     Get filename from content-disposition
   
7.     """
   
8.     if not cd:
   
9.         return None
   
10.     fname = re.findall('filename=(.+)', cd)
    
11.     if len(fname) == 0:
    
12.         return None
    
13.     return fname[0]
    
14. 
    
15. 
    
16. cookies = {
    
17.     'JSESSIONID': 'fa496ef8-4c46-49ba-b74c-dfc4c66a1970',
    
18. }
    
19. 
    
20. headers = {
    
21.     'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:95.0) Gecko/20100101 Firefox/95.0',
    
22.     'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8',
    
23.     'Accept-Language': 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
    
24.     'Accept-Encoding': 'gzip, deflate',
    
25.     'Connection': 'keep-alive',
    
26.     'Upgrade-Insecure-Requests': '1',
    
27. }
    
28. 
    
29. session = requests.Session()
    
30. index = session.get("http://read.nlc.cn/OutOpenBook/OpenObjectBook?aid=403&bid=17912.0", headers=headers, cookies=cookies).text
    
31. token = re.findall(r"tokenKey="(.*)" timeKey="(.*)" timeFlag", index)
    
32. myreader = token[0][0]
    
33. ktime = token[0][1]
    
34. headers = {
    
35.     'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:95.0) Gecko/20100101 Firefox/95.0',
    
36.     'Accept': '*/*',
    
37.     'Accept-Language': 'zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2',
    
38.     'Accept-Encoding': 'gzip, deflate',
    
39.     'myreader': myreader,
    
40.     'Range': 'bytes=0-1',
    
41.     'Connection': 'keep-alive',
    
42.     'Referer': 'http://read.nlc.cn/static/webpdf/lib/WebPDFJRWorker.js?h=0.29527337592322755',
    
43. }
    
44. 
    
45. pdf = session.get("http://read.nlc.cn/menhu/OutOpenBook/getReader?aid=403&bid=17912.0&kime=" + ktime + "&fime=" + ktime, allow_redirects=True, headers=headers, cookies=cookies)
    
46. filename = get_filename_from_cd(pdf.headers.get('content-disposition'))
    
47. open(filename, 'wb').write(pdf.content)

复制代码

sdqu

工具人上
zsbd

swsh007

这是国图最近发出来的古籍
免费在线看的

七年

爬       请你 喝茶