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
import re
from  datetime  import  *
import pandas

def gethits(url_1):
    li_id =re.search('_.*/(.*).html',url_1).groups(0)[0]
    hits = requests.get('http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(li_id)).text.split('.')[-1].rstrip('''');''').lstrip(''''html(''')
    return hits

def getdetail(url):
    res = requests.get(url)
    res.encoding = 'utf-8'
    
    soup = BeautifulSoup(res.text,'html.parser')
 
    news = {}
    news['url'] = url
    if(soup.select('.show-title')):
        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['source'] = re.search('来源：(.*)点击',info).group(1).strip()
        news['content'] = soup.select('.show-content')[0].text.strip()
        news['hits'] = gethits(url)
    else:
        pass
    return news

def onepage(url_page):
    res = requests.get(url_page)
    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

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

newstotal = []
newstotal.extend(onepage(url_main))

pages = int(soup.select('.a1')[0].text.rstrip('条'))//10+1

for i in range(2,pages+1):
    url_page = "http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html".format(i)
    
    newstotal.extend(onepage(url_page))

df = pandas.DataFrame(newstotal)
print(df.head())
df.to_excel('news.xlsx')