数据结构化与保存

def write(filename, content):
    f = open(filename, ‘a‘, encoding=‘utf-8‘)
    f.write(content)
    f.close()

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

#获得新闻点击次数
def getclick(link):
    newId = re.search(‘\_(.*).html‘, link).group(1).split(‘/‘)[1]
    click = requests.get(‘http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80‘.format(newId))
    return click.text.split(‘.html‘)[-1].lstrip("(‘").rstrip("‘);")


def getnewsdetail(link):
        resd = requests.get(link)
        resd.encoding = ‘utf-8‘
        soupd = BeautifulSoup(resd.text, ‘html.parser‘)

        content=soupd.select(‘.show-content‘)[0].text
        info=soupd.select(‘.show-info‘)[0].text
        time=re.search(‘(\d{4}.\d{2}.\d{2}\s\d{2}.\d{2}.\d{2})‘,info).group(1)
        newsdict={}
        newsdict[‘title‘]=soup.select(‘.show-title‘)[0].text
        if info.find(‘作者‘) > 0:
            newsdict[‘author‘] = re.search(‘作者：((.{2,4}\s|.{2,4}、|.{2,4}，|\w*\s){1,5})‘, info).group(1)
        else:
            newsdict[‘author‘] = ‘none‘
        if info.find(‘审核‘) > 0:
            newsdict[‘auditing‘] = re.search(‘审核：((.{2,4}\s|.{2,4}、|.{2,4}，|\w*\s){1,5})‘, info).group(1)
        else:
            newsdict[‘auditing‘] = ‘none‘
        if info.find(‘来源：‘) > 0:
            newsdict[‘source‘] = re.search(‘来源：(.*)\s*摄|点‘, info).group(1)
        else:
            newsdict[‘source‘] = ‘none‘
        newsdict[‘datetime‘]=datetime.strptime(time,‘%Y-%m-%d %H:%M:%S‘)
        newsdict[‘click‘]=getclick(link)
        newsdict[‘content‘]=content
        return newsdict



def getlistpage(listlink):
    res=requests.get(listlink)
    res.encoding=‘utf-8‘
    soup=BeautifulSoup(res.text,‘html.parser‘)
    pagelist=[]
    for news in soup.select(‘.new-list‘)[0].select(‘li‘):
        link = news.a.attrs[‘href‘]
        pagedict = getnewsdetail(link)
        pagelist.append(pagedict)
    return pagelist

def getnewstotal(link):
    res=requests.get(link)
    res.encoding=‘utf-8‘
    soup=BeautifulSoup(res.text,‘html.parser‘)
    return int(soup.select(‘.al‘)[0].text.rstrip(‘条‘))//10+1

listlink=‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘
Allfind=[]
pagelist=getlistpage(listlink)
Allfind.extend(pagelist)
listCount=getnewstotal(listlink)
pan = pandas.DataFrame(Allfind)
pan.to_excel(‘result.xlsx‘)
pan.to_csv(‘result.csv‘)
for i in range(2,listCount):
    listlink=‘http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html‘.format(i)
    Allfind=getlistpage(listlink)

print(pan[[‘click‘, ‘sources‘, ‘title‘]].head(6))