作者:痴情被撕碎的阳光 | 来源:互联网 | 2023-10-17 12:29
使用python输入PDF编号自动下载freepatentsonline.com的文档#!usrbinenvpython3#codingutf-8#Version:python3.
使用python输入PDF编号自动下载freepatentsonline.com的文档
#!/usr/bin/env python3
# coding=utf-8
# Version:python3.6.1
# File:requests_freepatentsonline_com.py
# Author:lgsp_Harold
import os
import requests
from lxml import etree
dir_path = './files/freepatentsonline_com/'
if not os.path.exists(dir_path):
os.makedirs(dir_path)
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:63.0) Gecko/20100101 Firefox/63.0',
}
while True:
number = input('(输入Q退出)输入pdf编号:').strip()
if number == 'Q':
break
url = 'https://www.freepatentsonline.com/' + number + '.pdf'
pdf_response = requests.get(url=url, headers=headers)
doc = etree.HTML(pdf_response.text)
download = doc.xpath('//center[@]/iframe/@src')[0]
# [url=https://s3.amazonaws.com/pdf.sumobrain.com/US9039490B2.pdf?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIAIBOKHYOLP4MBMRGQ%2F20210715%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20210715T000000Z&X-Amz-Expires=173822&X-Amz-SignedHeaders=host&X-Amz-Signature=ade0d0aad351dc65cb130810793964e11a6970120fe6bb3258a9728424db6a42#view=FitH]https://s3.amazonaws.com/pdf.sum ... 424db6a42#view=FitH[/url]
download_url = download.replace('#view=FitH', '')
file = requests.get(download_url, headers=headers)
file_path = './files/freepatentsonline_com/' + number + '.pdf'
with open(file_path, 'wb') as f:
f.write(file.content)
print('%s-PDF成功下载' % number)
略懂,略懂....