2 将新闻数据结构转化为字典列表
import pandas
import requests
import re
from bs4 import BeautifulSoup
from datetime import datetime
def writeNewsDatail(content):
f=open('gzccnews1.txt','a',encoding='utf-8')
f.write(content)
f.close()#dui
# 获取新闻点击次数
def getNewsId(url):#dui
newsId = re.findall(r'\_(.*).html', url)[0][-4:]
clickUrl = 'http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(newsId)
clickRes = requests.get(clickUrl)
# 利用正则表达式获取新闻点击次数
clickCount = int(re.search("hits').html('(.*)');", clickRes.text).group(1))
return clickCount
def getNewsDetail(newsUrl):#dui
# 读取新闻细节
resd = requests.get(newsUrl)
resd.encoding = "utf-8"
soupd = BeautifulSoup(resd.text, 'html.parser')#打开详情页并解析
news={}
news['title']=soupd.select('.show-title')[0].text
info = soupd.select(".show-info")[0].text # info相关内容
news['dt']=datetime.strptime(info.lstrip('发布时间:')[0:19],'%Y-%m-%d %H:%M:%S')
if info.find('来源:')>0:#作者:审核:来源:摄影:一样处理
news['source']=info[info.find('来源:'):].split()[0].lstrip('来源:')
else:
news['source']='none'
news['content'] = soupd.select(".show-content")[0].text.strip() # 正文
news['count'] = getNewsId(newsUrl)
news['newsUrl']=newsUrl
return(news)
def getListPage(pageUrl):#dui
res=requests.get(pageUrl)
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].attrs['href'] # 链接
newsList.append(getNewsDetail(newsUrl)) #把详情的字典插进列表(一个新闻是字典 多个新闻是列表)
return newsList
def getPageN(): #新闻列表页的总页数
res=requests.get('http://news.gzcc.cn/html/xiaoyuanxinwen/')
res.encoding='utf-8'
soup=BeautifulSoup(res.text,'html.parser')
n=int(soup.select('.a1')[0].text.rstrip('条'))
return(n//10+1)
newsTotal=[]
n=getPageN()
p= [2, n]
for i in p:
listPageUrl = "http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html".format(i)
print(listPageUrl)
newsTotal.extend(getListPage(listPageUrl))
for news in newsTotal:
print(news)
3·安装pandas,使用pandas.Dataframe(newstotal)创建DataFrame对象df.
4.通过df将提取的数据保存到cvs或excel文件
5.
df.head(6)
df[['click','title','source']]
df[(df['click']>3000) | (df['source']=='学校综合办')]
list=['学生工作处','国际学院']
print(df[df['sources'].isin(list)])