数据结构化与保存

Posted 2020-10-11

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

安装包

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

def getTheUserClick(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 getTheContent(url001):
    res = requests.get(url001)
    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[‘content‘]=soup.select(‘.show-content‘)[0].text.strip()
    news[‘click‘]=getTheUserClick(url001)
    return (news)

def getOnePage(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(getTheContent(news.select(‘a‘)[0][‘href‘]))
    return(newsls)
newstotal=[]
url = ‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘
res = requests.get(url)
res.encoding = ‘utf-8‘
soup = BeautifulSoup(res.text, ‘html.parser‘)
pages = int(soup.select(‘.a1‘)[0].text.rstrip(‘条‘))//10+1

for i in range(2,pages+1):
    url001=‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘
    newstotal.extend(getOnePage(url001))
df =pandas.DataFrame(newstotal)
df.to_excel(‘gzccnews.xlsx‘)
#df.to_docx(‘gzccnews.docx‘)