爬虫|巨潮资讯网上市公司年报爬取

爬虫|巨潮资讯网上市公司年报爬取

import pandas as pd
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
import time
import requests
import os
import random
from PyPDF2 import PdfFileReader

chrome_options = webdriver.ChromeOptions()
chrome_options.add_argument('--start-maximized')
browser = webdriver.Chrome(options=chrome_options)

#os.makedirs('D:\\公司年报')  #在D盘创建文件夹，若重复运行，注释此行

#解析网址
def get_html_content(url):
    header = {
   
        "User-Agent":"Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.183 Mobile Safari/537.36"
        }
    r = requests.get(url,headers = header)
    if r.status_code == 200:
        r.encoding = 'utf-8'
        #print(r.content)
        return r.content
    else:
        return None
  
#保存pdf   
def report_save(url,pdf_name):
    report = get_html_content(url)
    path = "D:\