1.从新闻url获取新闻详情: 字典,anews
import requests from bs4 import BeautifulSoup from datetime import datetime import re def click(xbk): id=re.findall('(d{1,5})',xbk)[-1] clickUrl='http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(id) resClick=requests.get(clickUrl) newsClick=int(resClick.text.split('.html')[-1].lstrip("('").rstrip("');")) return newsClick def newsdt(showinfo): newsDate=showinfo.split()[0].split(":")[1] newsTime=showinfo.split()[1] newsDT=newsDate+' '+newsTime dt=datetime.strptime(newsDT,'%Y-%m-%d %H:%M:%S') return dt def anewsDate(xbk): newsDetail={} res=requests.get(xbk) res.encoding='utf-8' soup=BeautifulSoup(res.text,'html.parser') newsDetail['nenewsTitle']=soup.select('.show-title')[0].text showinfo=soup.select('.show-info')[0].text newsDetail['newsDT']=newsdt(showinfo) newsDetail['newsClick']=click(newsUrl) return newsDetail newsZD='http://news.gzcc.cn/html/2005/xiaoyuanxinwen_0710/4.html' anewsDate(newsXBK) res = requests.get('http://news.gzcc.cn/html/xiaoyuanxinwen/') res.encoding='utf-8' soup = BeautifulSoup(res.text,'html.parser') for news in soup.select('li'): if len(news.select('.news-list-title'))>0: newsUrl=news.select('a')[0]['href'] print(anews(newsUrl))
运行结果如下:
3.生成所页列表页的url并获取全部新闻 :列表extend(列表) allnews
ZD='http://news.gzcc.cn/html/xiaoyuanxinwen/' res=requests.get(ZD) res.encoding='utf-8' soup = BeautifulSoup(res.text,'html.parser') newsList=[] for news in soup.select('li'): if len(news.select('.news-list-title'))>0: newsUrl=news.select('a')[0]['href'] newsDesc=news.select('.news-list-description')[0].text newsDict=anews(newsUrl) newsDict['description']=newsDesc newsList.append(newsDict) newsList
4.设置合理的爬取间隔
import time
import random
time.sleep(random.random()*3)
5.用pandas做简单的数据处理并保存
保存到csv或excel文件
newsdf.to_csv(r'F:duym爬虫gzccnews.csv')
保存到数据库
import sqlite3
with sqlite3.connect('gzccnewsdb.sqlite') as db:
newsdf.to_sql('gzccnewsdb',db)