python爬虫智能翻页批量下载文件的实例详解

import requests
import pandas as pd
from lxml import etree
import re
import os

baseUrl ='http://www.jkl.com.cn/cn/invest.aspx' # 爬取页面的数据
heade ={
'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) 
Chrome/81.0.4044.92 Safari/537.36'
}
res =requests.get(url=baseUrl,headers=heade).text  
# print(res.text)
html = etree.HTML(res)
res =requests.get(url=baseUrl,headers=heade).text  #  设置变量接受 基础页的响应数据
# print(res.text)
html = etree.HTML(res)

data_name = html.xpath('//div[@class="infoLis"]//a/text()') # 投资者列表的名字
data_link = html.xpath('//div[@class="infoLis"]//@href')  # 全部列表的链接
name = [data_name.strip() for data_name in data_name]  # 通过for循环去掉空字符
link = ['http://www.jkl.com.cn/cn/'+ data_link for data_link in data_link] # 拼接字符串
# 合并为字典，方便保存文件
file = dict(zip(name,link))

for name,link in file.items():
  name=name.replace('/','.')
  name=name.replace('...','报表')
  # 上面的把文件名带特许字符的 强制转换为我们想要的文本类型
  path = 'E:/'+ name
  if not os.path.exists(path):
    os.mkdir(path)
    #建立储存位置

  res_list = requests.get(url = link, headers = heade).text
  list_html = etree.HTML(res_list)
  # print(html_erJi) 解析每个分类的链接
  weiYe = list_html.xpath('//a[text()="尾页"]/@href')
  # print(html_weiye)
  # 拿到尾页信息
  if weiYe !=[]:
    # 正则提取尾页信息
    get_weiYe =re.search("(\d+)'\)",html_weiye[0])
    get_yeMa = get_html_weiYe.group(1)
  else:
    get_yeMa=1
  # print(get_html_yeMa) 看看是不是提取成功

  for get_yeMa in range(1,int(get_yeMa)+1): # 翻页
    yaMa= {
    '__EVENTTARGET': 'AspNetPager1',
    '__EVENTARGUMENT': get_yeMa
    }
    get_lei_html = requests.get(url = link, headers = heade, params = yaMa).text
    res3 =etree.HTML(get_lei_html)
    # print(res3)
    pdf_name = res3.xpath('//div[@class="newsLis"]//li/a/text()')
    # print(pdf_name)
    pdf_url = res3.xpath('//div[@class="newsLis"]//li//@href')

 pdf_names = [pdf_name.strip() for pdf_name in pdf_name]
 # print(pdf_names)
 if all(pdf_url):
      pdf_urls = ['http://www.jkl.com.cn'+pdf_url for pdf_url in pdf_url]
      # print(pdf_url)
      pdf_data=dict(zip(pdf_names,pdf_urls))  # pdf地址和名字整合为字典
      for pdfName,pdfUrl in pdf_data.items():
        pdfName =pdfName.replace('/','.')
        res_pdf= requests.get(url =pdfUrl,headers=heade).content
        houZui = pdfUrl.split('.')[-1]
        pdf_pash = path + '/' + pdfName + '.'+ houZui  # 
        # print(pdf_pash)
        with open(pdf_pash,'wb') as f:
          f.write(res_pdf)
          print(pdfName,'下载成功')