爬取全部的校园新闻
2019-04-08 18:02 CMis180kg 阅读(173) 评论(0) 编辑 收藏 举报作业要求来源于:https://edu.cnblogs.com/campus/gzcc/GZCC-16SE2/homework/2941
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 import time import random import pandas as pd import sqlite3 def click(url): id = re.findall('(\d{1,5})',url)[-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] newDT = newsDate+' '+newsTime dt = datetime.strptime(newDT,'%Y-%m-%d %H:%M:%S') return dt def anews(url): newsDetail = {} res = requests.get(url) 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 def alist(url): res=requests.get(listUrl) 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) return newsList newsUrl = 'http://news.gzcc.cn/html/2019/xiaoyuanxinwen_0323/11636.html' anews(newsUrl) 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)) allnews=[] for i in range(81,90): listUrl='http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i) allnews.extend(alist(listUrl)) len(allnews) pd.Series(anews) newsdf=pd.DataFrame(allnews) for i in range(5): time.sleep(random.random()*3) newsdf.to_csv(r'F:\cm.csv')
执行结果如下图所示:
2.从列表页的url获取新闻url:列表append(字典) alist
listUrl='http://news.gzcc.cn/html/xiaoyuanxinwen/' res = requests.get(listUrl) 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) print(newsList)
执行结果如下图所示:
3.生成所页列表页的url并获取全部新闻 :列表extend(列表) allnews
*每个同学爬学号尾数开始的10个列表页
import requests from bs4 import BeautifulSoup from datetime import datetime import re import time import random import pandas as pd import sqlite3 def click(url): id = re.findall('(\d{1,5})',url)[-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] newDT = newsDate+' '+newsTime dt = datetime.strptime(newDT,'%Y-%m-%d %H:%M:%S') return dt def anews(url): newsDetail = {} res = requests.get(url) 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 def alist(url): res=requests.get(listUrl) 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) return newsList newsUrl = 'http://news.gzcc.cn/html/2019/xiaoyuanxinwen_0323/11636.html' anews(newsUrl) 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'] listUrl='http://news.gzcc.cn/html/xiaoyuanxinwen/' res = requests.get(listUrl) 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) print(allnews) allnews=[] for i in range(81,90): listUrl='http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i) allnews.extend(alist(listUrl)) len(allnews) pd.Series(anews) newsdf=pd.DataFrame(allnews) for i in range(5): time.sleep(random.random()*3) newsdf.to_csv(r'F:\cm.csv')
4.设置合理的爬取间隔
print(allnews) allnews=[] for i in range(81,90): listUrl='http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i) allnews.extend(alist(listUrl)) len(allnews) pd.Series(anews) newsdf=pd.DataFrame(allnews) for i in range(5): print(i) time.sleep(random.random()*3) print(newsdf)
执行效果如下图所示:
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)
执行效果如下图所示: