作业要求：https://edu.cnblogs.com/campus/gzcc/GZCC-16SE1/homework/3002
0.从新闻url获取点击次数，并整理成函数
- newsUrl
- newsId(re.search())
- clickUrl(str.format())
- requests.get(clickUrl)
- re.search()/.split()
- str.lstrip(),str.rstrip()
- int
- 整理成函数
- 获取新闻发布时间及类型转换也整理成函数
#获取点击次数 def click(url): newsId=re.search('/(\d*).html',url).group(1) clickUrl='http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(newsId) resClick=requests.get(clickUrl) #将点击次数分隔出来并转化成int类型 newsClick=int(re.search("hits'[)].html[(]'(\d+)'[)]",resClick).groups(1)) return newsClick #获取新闻时间 def newsdt(showinfo): newsDate=showinfo.split()[0].split(':')[1] newsTime=showinfo.split()[1] newsDT=newsDate+' '+newsTime #将时间字符串转为datatime类型 dt=datetime.strptime(newsDT,'%Y-%m-%d %H:%M:%S') return dt
1.从新闻url获取新闻详情： 字典,anews
#获取新闻信息 def anews(url): newsDetail={} # 新建字典 res=requests.get(url) res.encoding='utf-8' s=BeautifulSoup(res.text,'html.parser') newsDetail['newsTitle']=s.select('.show-title')[0].text # 新闻题目 showinfo=s.select('.show-info')[0].text newsDetail['newsDT']=newsdt(showinfo) # 新闻时间 newsDetail['newsClick']=click(url) # 点击次数 return newsDetail
2.从列表页的url获取新闻url：列表append(字典) alist
#获取新闻列表页中的新闻url及描述 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'] newsDest=news.select('.news-list-description')[0].text newsDict=anews(newsUrl) newsDict['newsUrl'] = newsUrl #添加新闻url newsDict['description']=newsDest #添加新闻描述 newsList.append(newsDict) return newsList listUrl= 'http://news.gzcc.cn/html/xiaoyuanxinwen/' alist(listUrl)
运行截图：
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
#获取新闻第48-第58页的所有新闻 allnews = [] for i in range(48,58): listUrl='http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i) allnews.extend(alist(listUrl))
4.设置合理的爬取间隔
import time
import random
time.sleep(random.random()*3)
#设置合理的爬取间隔 for i in range(5): 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')
#保存文件 pd.Series(allnews) newsdf=pd.DataFrame(allnews) newsdf.to_csv(r'F:\news.csv')
运行截图：
6.完整代码
import requests from bs4 import BeautifulSoup from datetime import datetime import re import sqlite3 import pandas as pd import time import pandas import random #获取点击次数 def click(url): newsId=re.search('/(\d*).html',url).group(1) clickUrl='http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(newsId) resClick=requests.get(clickUrl) #将点击次数分隔出来并转化成int类型 newsClick=int(resClick.text.split('.html')[-1].lstrip("('").rstrip("');")) return newsClick #获取新闻时间 def newsdt(showinfo): newsDate=showinfo.split()[0].split(':')[1] newsTime=showinfo.split()[1] newsDT=newsDate+' '+newsTime #将时间字符串转为datatime类型 dt=datetime.strptime(newsDT,'%Y-%m-%d %H:%M:%S') return dt #获取新闻信息 def anews(url): newsDetail={} # 新建字典 res=requests.get(url) res.encoding='utf-8' s=BeautifulSoup(res.text,'html.parser') newsDetail['newsTitle']=s.select('.show-title')[0].text # 新闻题目 showinfo=s.select('.show-info')[0].text newsDetail['newsDT']=newsdt(showinfo) # 新闻时间 newsDetail['newsClick']=click(url) # 点击次数 return newsDetail #获取新闻列表页中的新闻url及描述 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'] newsDest=news.select('.news-list-description')[0].text newsDict=anews(newsUrl) newsDict['newsUrl'] = newsUrl #添加新闻url newsDict['description']=newsDest #添加新闻描述 newsList.append(newsDict) return newsList listUrl='http://news.gzcc.cn/html/xiaoyuanxinwen/' alist(listUrl) res=requests.get(listUrl) 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'] i=int(soup.select('#pages')[0].text.split('..')[1].rstrip(' 下一页 ')) #获取新闻第48-第58页的所有新闻 allnews=[] for i in range(48,58): listUrl='http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i) allnews.extend(alist(listUrl)) 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'] #保存文件 pd.Series(anews) newsdf=pd.DataFrame(allnews) newsdf.to_csv(r'F:\news.csv') #设置合理的爬取间隔 for i in range(5): time.sleep(random.random()*3) print(newsdf)
