数据结构化与保存

import requests
from bs4 import BeautifulSoup
from datetime import datetime
import re
import pandas

#获取点击次数
def getClickCount(newsUrl):
    newId=re.search('\_(.*).html',newsUrl).group(1).split('/')[1]
    clickUrl="http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80".format(newId)
    clickStr = requests.get(clickUrl).text
    count = re.search("hits'\).html\('(.*)'\);", clickStr).group(1)
    return count

#获取新闻详情
def getNewsDetail(newsurl):
    resd=requests.get(newsurl)
    resd.encoding='utf-8'
    soupd=BeautifulSoup(resd.text,'html.parser')

    news={}
    news['title']=soupd.select('.show-title')[0].text
    # news['newsurl']=newsurl
    info=soupd.select('.show-info')[0].text
    news['dt']=datetime.strptime(info.lstrip('发布时间:')[0:19],'%Y-%m-%d %H:%M:%S')
    news['click'] = int(getClickCount(newsurl))
    if info.find('来源')>0:
        news['source'] =info[info.find('来源:'):].split()[0].lstrip('来源:')
    else:
        news['source']='none'
    if info.find('作者:') > 0:
        news['author'] = info[info.find('作者:'):].split()[0].lstrip('作者:')
    else:
        news['author'] = 'none'
    # news['content']=soupd.select('.show-content')[0].text.strip()

    #获取文章内容并写入到文件中
    content=soupd.select('.show-content')[0].text.strip()
    writeNewsContent(content)

    return news

def getListPage(listPageUrl):
    res=requests.get(listPageUrl)
    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:
            a=news.select('a')[0].attrs['href']
            newsList.append(getNewsDetail(a))
    return (newsList)

#数据写入文件
def writeNewsContent(content):
    f=open('gzccNews.txt','a',encoding='utf-8')
    f.write(content)
    f.close()

def getPageNumber():
    ListPageUrl="http://news.gzcc.cn/html/xiaoyuanxinwen/"
    res=requests.get(ListPageUrl)
    res.encoding='utf-8'
    soup=BeautifulSoup(res.text,'html.parser')
    n = int(soup.select('.a1')[0].text.rstrip(''))//10+1
    return n


newsTotal=[]
firstPage='http://news.gzcc.cn/html/xiaoyuanxinwen/'
newsTotal.extend(getListPage(firstPage))

n=getPageNumber()
for i in range(n,n+1):
    listUrl= 'http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i)
    newsTotal.extend(getListPage(listUrl))

df=pandas.DataFrame(newsTotal)
# df.to_excel("news.xlsx")

# print(df.head(6))
# print(df[['author','click','source']])
# print(df[df['click']>3000])

sou=['国际学院','学生工作处']
print(df[df['source'].isin(sou)])

 

posted on 2018-04-12 20:43  184陈楚浩  阅读(102)  评论(0编辑  收藏  举报