10-19数据结构化与保存

>>> import requests
>>> import pandas
>>> from bs4 import BeautifulSoup
>>> from datetime import datetime
>>> def Click(newurl):
    id = re.search('_(.*).html', newurl).group(1).split('/')[1]
    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(click)
>>> def getdetail(url): #单条新闻链接，字典
    read = request.get(url)
    res.encoding = 'utf-8'
    soup = BeautifulSoup(res.text, 'html.parser')
    new={}
    news['url']=url
    news['title']=soup.select('.show-title')[0].text
    info = soup.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'] = getclick(url)
    return(news)
>>> def onepage(pageurl):#新闻列表
    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

 

转载于:https://www.cnblogs.com/wadee/p/7691639.html