import requests
from urllib import request
import re
import os
import random
headers = [{
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/78.0.3904.116 Safari/537.36'},
{
'User-Agent': 'Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1)'},
{
'User-Agent': 'Mozilla/5.0 (compatible; rv:1.9.1) Gecko/20090702 Firefox/3.5'},
{
'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/534.16 (KHTML, like Gecko) Chrome/10.0.648.133'},
{
'User-Agent': 'Mozilla/5.0 (compatible; rv:2.0) Gecko/20110101 Firefox/4.0'},
{
'User-Agent': 'Mozilla/5.0 (compatible) AppleWebKit/534.21 (KHTML, like Gecko) Chrome/11.0.682.0 Safari/534.21'},
{
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:6.0.2) Gecko/20100101 Firefox/6.0.2'},
爬虫上交所公告并批量下载pdf
最新推荐文章于 2024-04-01 14:44:30 发布
本文介绍如何使用Python爬虫技术从上海证券交易所网站抓取公告信息,并实现批量下载公告的PDF文件,涉及到的工具包括requests、BeautifulSoup和MySQL数据库。
摘要由CSDN通过智能技术生成