Python爬虫爬取新闻资讯案例详解

# -*- coding: UTF-8 -*-

import requests,time,re
from fake_useragent import UserAgent
from lxml import etree

class RandomHeaders(object):
  ua=UserAgent()
  @property
  def random_headers(self):
    return {
      'User-Agent': self.ua.random,
    }

class Spider(RandomHeaders):
  def __init__(self,url):
    self.url=url


  def parse_home_list(self,url):
    response=requests.get(url,headers=self.random_headers).content.decode('utf-8')
    req=etree.HTML(response)
    href_list=req.xpath('//ul[@class="news-list"]/li/a/@href')
    print(href_list)
    for href in href_list:
      item = self.parse_detail(f'https://yz.chsi.com.cn{href}')
      yield item


  def parse_detail(self,url):
    print(f">>正在爬取{url}")
    try:
      response = requests.get(url, headers=self.random_headers).content.decode('utf-8')
      time.sleep(2)
    except Exception as e:
      print(e.args)
      self.parse_detail(url)
    else:
      req = etree.HTML(response)
      try:
        h2=req.xpath('//div[@class="title-box"]/h2/text()')[0]
        h2=self.validate_title(h2)
        author=req.xpath('//div[@class="title-box"]/span[@class="news-from"]/text()')[0]
        details=req.xpath('//div[@class="content-l detail"]/p/text()')
        detail='\n'.join(details)
        print(h2, author, detail)
        self.save(h2, author, detail)
        return h2, author, detail
      except IndexError:
        print(">>>采集出错需延时，5s后重试..")
        time.sleep(5)
        self.parse_detail(url)


  @staticmethod
  def validate_title(title):
    pattern = r"[\/\\\:\*\?\"\<\>\|]"
    new_title = re.sub(pattern, "_", title) # 替换为下划线
    return new_title



  def save(self,h2, author, detail):
    with open(f'{h2}.txt','w',encoding='utf-8') as f:
      f.write('%s%s%s%s%s'%(h2,'\n',detail,'\n',author))

    print(f"保存{h2}.txt文本成功！")
  def get_tasks(self):
    data_list = self.parse_home_list(self.url)
    for item in data_list:
      yield item
if __name__=="__main__":
  url="https://yz.chsi.com.cn/kyzx/jyxd/"
  spider=Spider(url)
  for data in spider.get_tasks():
    print(data)