数据结构化与保存

1.结构化:

  • 单条新闻的详情字典:news
  • 一个列表页所有单条新闻汇总列表:newsls.append(news)
  • 所有列表页的所有新闻汇总列表:newstotal.extend(newsls)

2.转换成pandas的数据结构DataFrame

3.从DataFrame保存到excel

4.从DataFrame保存到sqlite3数据库

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

res=requests.get('http://news.gzcc.cn/html/xiaoyuanxinwen/')
res.encoding='utf-8'
soup=BeautifulSoup(res.text,'html.parser')

def getclick(newsurl):
    id=re.search('_(.*).html',newsurl).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):
    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=[]
newstotal.extend(onepage('http://news.gzcc.cn/html/xiaoyuanxinwen/'))
n=int(soup.select('.a1')[0].text.rstrip(''))
pages=n//10+1

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

#print(len(newstotal))
df=pandas.DataFrame(newstotal)
print(df.head())
print(df['title'])
df.to_excel('gzccnews.xlsx')
#with sqlite3.connect('gzccnewsdb2.sqlite') as db:
#df.to_sql('gzccnewsdb2',con=db)

从DataFrame保存到excel:

 

posted on 2017-10-19 19:42  46陈远钊  阅读(112)  评论(0编辑  收藏  举报