这个站资料能扒不 - 全球主机交流论坛

import requests
import re
def get_filename_from_cd(cd):
"""
Get filename from content-disposition
"""
if not cd:
return None
fname = re.findall('filename=(.+)', cd)
if len(fname) == 0:
return None
return fname[0]
cookies = {
'JSESSIONID': 'fa496ef8-4c46-49ba-b74c-dfc4c66a1970',
}
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:95.0) Gecko/20100101 Firefox/95.0',
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8',
'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',
'Accept-Encoding': 'gzip, deflate',
'Connection': 'keep-alive',
'Upgrade-Insecure-Requests': '1',
}
session = requests.Session()
index = session.get("http://read.nlc.cn/OutOpenBook/OpenObjectBook?aid=403&bid=17912.0", headers=headers, cookies=cookies).text
token = re.findall(r"tokenKey="(.*)" timeKey="(.*)" timeFlag", index)
myreader = token[0][0]
ktime = token[0][1]
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:95.0) Gecko/20100101 Firefox/95.0',
'Accept': '*/*',
'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',
'Accept-Encoding': 'gzip, deflate',
'myreader': myreader,
'Range': 'bytes=0-1',
'Connection': 'keep-alive',
'Referer': 'http://read.nlc.cn/static/webpdf/lib/WebPDFJRWorker.js?h=0.29527337592322755',
}
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)
filename = get_filename_from_cd(pdf.headers.get('content-disposition'))
open(filename, 'wb').write(pdf.content)

复制代码