数据结构化与保存

Posted 2020-10-11 18-刘卓辉

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

def getclick(newsurl):
    num = re.search(‘_(.*).html‘,newsurl)
    id = num.group(1)[5:]
    clickurl = ‘http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80‘.format(id)
    click = int(requests.get(clickurl).text.split(‘.‘)[-1].lstrip("html(‘").rstrip("‘);"))
    return(int(click))

def getdetail(url):
    resd = requests.get(url)
    resd.encoding = ‘utf-8‘
    soupd = BeautifulSoup(resd.text,‘html.parser‘)
    news = {}
    news[‘url‘] = url
    news[‘title‘] = soupd.select(‘.show-title‘)[0].text
    info = soupd.select(‘.show-info‘)[0].text
    news[‘dt‘]=datetime.strptime(info.lstrip(‘发表时间：‘)[0:19],‘%Y-%m-%d %H:%M:%S‘)
    news[‘source‘] = re.search(‘来源：(.*)点击‘,info).group(1).strip()
    news[‘click‘] = getclick(url)
    return (news)

def onepage(pageurl):
    res = requests.get(pageurl)
    res.encoding = ‘utf-8‘
    soup = BeautifulSoup(res.text,‘html.parser‘)
    newsls = []
    for news in soup.select(‘li‘):
        if len(news.select(‘.news-list-title‘))>0:
            newsls.append(getdetail(news.select(‘a‘)[0][‘href‘]))
    return(newsls)

newstotal = []
gzccurl = ‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘
newstotal.extend(onepage(gzccurl))

res = requests.get(gzccurl)
res.encoding = ‘utf-8‘
soup = BeautifulSoup(res.text,‘html.parser‘)
n = int(soup.select(‘.a1‘)[0].text.rstrip(‘条‘))
pages = n//10+1  #计算多少条多少页

for i in range(2,3):
    listurl = ‘http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html‘.format(i)
    newstotal.extend(onepage(listurl))


lf=pandas.DataFrame(newstotal)

df.to_excel(‘gzccnews.xlsx‘)


with sqlital.connect(‘gzccnewsdb.sqlite‘)  as db:
    df.to_sql(‘gzccnewsdb‘,con=db)