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
import re
import pandas
from bs4 import BeautifulSoup
import sqlite3

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

def getclick(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(listurl):
    res = requests.get(listurl)
    res.encoding = ‘utf-8‘
    soup = BeautifulSoup(res.text, ‘html.parser‘)
    news={}
    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:‘)
    #news[‘source‘]=re.search(‘来源:(.*)点击‘,info).group(1).strip()
    news[‘content‘]=soup.select(‘.show-content‘)[0].text.strip()
    news[‘click‘]=getclick(listurl)
    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=[]
for i in range(2,3):
    listurl=‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘
    newstotal.extend(onepage(listurl))
df =pandas.DataFrame(newstotal)
df.to_excel(‘gzccnews.xlsx‘)

with sqlite3.connect(‘gzccnews_db.sqlite‘) as db:
   df.to_sql(‘news_table‘,con = db)