python爬虫入门（实践）

python爬虫入门（实践）

一、对目标网站进行分析

二、博客爬取

1. 获取博客所有h2标题的路由

   1. 确定目标，查看源码
      

   2. 代码实现

      """
      获取博客所有h2标题的路由
      """
      
      url = "http://www.crazyant.net"
      
      import requests
      from bs4 import BeautifulSoup
      
      #发送请求，获取页面所有内容
      r = requests.get(url)
      if r.status_code != 200:
          raise Exception("请求失败") # 抛出异常
      html_doc = r.text
      
      # 解析html，获取对应信息
      soup = BeautifulSoup(html_doc,"html.parser")
      
      h2_nodes = soup.find_all("h2",class_="entry-title")
      
      for h2_node in h2_nodes:
          link = h2_node.find("a")
          print(link["href"],link.get_text())
      

2. 通过标题爬取所有博客文章

   """
   爬取所有博客文章
   """
   import re
   
   from utils import url_manager
   import requests
   from bs4 import BeautifulSoup
   
   root_url="http://www.crazyant.net"
   
   # 将root_url添加到urls中
   urls = url_manager.UrlManager()
   urls.add_new_url(root_url)
   
   # 获取所有页面内容，并保存到文件
   fout = open("craw_all_pages.txt","w",encoding="utf-8")
   while urls.has_new_url():
       curr_url = urls.get_url()
       r = requests.get(curr_url,timeout=2)
       if r.status_code != 200:
           print("请求失败",curr_url)
           continue
       soup = BeautifulSoup(r.text,"html.parser")
       title = soup.title.string # 获取标题
   
       fout.write('%s\t%s\n' % (curr_url, title))# 写入文件
       fout.flush()# 刷新缓冲区,直接写入文件
       print("success: %s, %s, %d"%(curr_url,title,len(urls.new_urls)))
   
       # 获取所有链接, 并添加到urls中
       links = soup.find_all("a")
       for link in links:
           href = link.get("href")
           if href is None:
               continue
           pattern = r"^http://www.crazyant.net/\d+.html$" # 匹配规则,匹配以http://www.crazyant.net/开头，并且以.html结尾的url
           # 正则匹配, 返回一个匹配对象，如果没有匹配到，返回None
           if re.match(pattern,href):
               urls.add_new_url(href)
   
   fout.close()
   

• 运行结果