Python爬虫批量下载Zabbix官方文档PDF实战

Dylan

发布时间：2026-10-13 | 3人浏览过

原创

本文介绍使用Python爬虫批量下载Zabbix官方文档的方法。通过requests获取页面链接，利用正则表达式解析目录结构，并拼接导出PDF参数实现批量下载。代码包含错误处理与延时机制，适合需要离线查阅技术文档的场景。

Python批量下载Zabbix文档实现

本文详细讲解如何利用Python编写爬虫程序，实现Zabbix官方文档的批量下载功能。文中提供了完整的代码示例，涵盖页面解析、链接提取及文件保存等关键环节，对从事运维开发或技术研究的读者具有较高的参考价值。

核心代码实现


# -*- coding: UTF-8 -*-
import requests,re,time
url = 'https://www.zabbix.com/documentation/3.4/zh/manual'
base_url = 'https://www.zabbix.com/documentation/3.4/'
seconds = 1
err_url = []
def get_urls():
  res = requests.get(url)
  content = res.text
  pattern = re.compile(r"indexmenu_4848130395ca30b274d8bd.add[(]'(zh/manual.*?)[']", re.S)
  routes = pattern.findall(content)
  urls = [base_url+item for item in routes]
  return urls 
def download(url):
  download_url = url + "?do=export_pdf"
  print("当前下载url:")
  print(download_url)
  res = requests.get(url)
  if res.status_code == 200 :
    pattern = re.compile(r"<title>(.*?)</title>", re.S)
    title = pattern.findall(res.text)[0].encode("utf-8")
    try:
      filename = title.replace('\\','-').replace('/','-').replace('"','-').replace('*','-').replace('?','-').replace(':','-').replace('<','-').replace('>','-').replace('|','-')
    except Exception:
       title = pattern.findall(res.text)[0]
    filename = title.replace('\\','-').replace('/','-').replace('"','-').replace('*','-').replace('?','-').replace(':','-').replace('<','-').replace('>','-').replace('|','-')
    file = filename + '.pdf'
    res = requests.get(download_url)
    if res.status_code == 200 :
      with open(file,"wb") as f:
        f.write(res.content)
      print('下载成功')
    else:
      print('下载失败')
      err_url.append(download_url)
  else:
    print('获取文件名失败，停止当前下载')
    err_url.append(download_url) 
def downloads(urls):
  for url in urls:
    download(url)
    time.sleep( seconds )
  if len(err_url) :
    print("下载失败的URL:")
    print(err_url) 
def main():
  print("下载开始")
  urls = get_urls()
  downloads(urls)
  print("下载完成") 
if __name__ == '__main__':
  main()