Python爬蟲實戰案例：爬取新聞資訊

前言

本文的文字及圖片來源於網路,僅供學習、交流使用,不具有任何商業用途,版權歸原作者所有,如有問題請及時聯繫我們以作處理。

一個簡單的Python資訊採集案例，列表頁到詳情頁，到數據保存，保存為txt文檔，網站網頁結構算是比較規整，簡單清晰明瞭，資訊新聞內容的採集和保存！

應用到的庫

requests，time，re，UserAgent，etree

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

列表頁面

列表頁，鏈接xpath解析

href_list=req.xpath('//ul[@class="news-list"]/li/a/@href')

詳情頁

內容xpath解析

h2=req.xpath('//div[@class="title-box"]/h2/text()')[0]
author=req.xpath('//div[@class="title-box"]/span[@class="news-from"]/text()')[0]
details=req.xpath('//div[@class="content-l detail"]/p/text()')

內容格式化處理

detail='\n'.join(details)

標題格式化處理，替換非法字元

pattern = r"[\/\\\:\*\?\"\<\>\|]"
new_title = re.sub(pattern, "_", title)  # 替換為下劃線

保存數據，保存為txt文本

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！")

遍曆數據採集，yield處理

def get_tasks(self):
    data_list = self.parse_home_list(self.url)
    for item in data_list:
        yield item

程式運行效果

程式採集效果

附源碼參考：

#研招網考研資訊採集
#20200710 by微信：huguo00289
# -*- 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(">>>採集出錯需延時，5s後重試..")
                time.sleep(5)
                self.parse_detail(url)


    @staticmethod
    def validate_title(title):
        pattern = r"[\/\\\:\*\?\"\<\>\|]"
        new_title = re.sub(pattern, "_", title)  # 替換為下劃線
        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)