数据结构化与保存

def writeNewsDetail(content):# 将新闻的正文内容保存到文本文件。
    f=open(‘gzccNews.txt‘,‘a‘,encoding=‘utf-8‘)
    f.write(content)
    f.close()

import re
import requests
import pandas
import requests
from bs4 import BeautifulSoup
from datetime import datetime
 
def getClickCount(url):
    newId=re.findall(r‘\_(.*).html‘,url)[0][-4:]
    clickUrl = ‘http://oa.gzcc.cn/api.php?op=count&id=8249&modelid=80‘.format(newId)
    clickRes = requests.get(clickUrl)
    clickCount = int(re.search("hits‘\).html\(‘(.*)‘\);", clickRes.text).group(1))
    return clickCount
#将获取新闻详情的代码定义成一个函数 def getNewDetail(newsUrl):
def getNewsDetail(newsUrl):#一篇新闻的全部消息
    resd=requests.get(newsUrl)
    resd.encoding = ‘utf-8‘
    soupd = BeautifulSoup(resd.text, ‘html.parser‘)#打开新闻详情页并解析
 
    news={}
    news[‘title‘] = soupd.select(‘.show-title‘)[0].text
    info = soupd.select(‘.show-info‘)[0].text
    news[‘dt‘] = datetime.strptime(info.lstrip(‘发布时间:‘)[0:19], ‘%Y-%m-%d %H:%M:%S‘)
    if info.find(‘来源：‘) > 0:
        source = info[info.find(‘来源：‘):].split()[0].lstrip(‘来源：‘)
    else:
        source = ‘none‘
    if info.find(‘作者：‘) > 0:
        source = info[info.find(‘作者：‘):].split()[0].lstrip(‘作者：‘)
    else:
        source = ‘none‘
    news[‘content‘]=soupd.select(‘.show-content‘)[0].text.strip()
 
    # writeNewsDetail(content)
    news[‘click‘] = getClickCount(newsUrl)
    news[‘newsUrl‘]=newsUrl
    return (news)
 
def getNewsList(pageUrl):
  res=requests.get(pageUrl)
  res.encoding = ‘utf-8‘
  soup = BeautifulSoup(res.text, ‘html.parser‘)
  for news in soup.select(‘li‘):
    if len(news.select(‘.news-list-title‘))>0:
        # print(news.select(‘.news-list-title‘))
        #t=news.select(‘.news-list-title‘)[0].text#取标题
        #dt=news.select(‘.news-list-info‘)[0].contents[0].text#取日期
        newsUrl=news.select(‘a‘)[0].attrs[‘href‘]#取链接
        getNewsDetail(newsUrl)
        break
 
def getListPage(pageUrl):
    res=requests.get(pageUrl)
    res.encoding=‘utf-8‘
    soup=BeautifulSoup(res.text,‘html.parser‘)
    newsList=[]
    for news in  soup.select(‘li‘):
        if len(news.select(‘.news-list-title‘))>0:
            newsUrl=news.select(‘a‘)[0].attrs[‘href‘]
            newsList.append(getNewsDetail(newsUrl))
    return (newsList)
 
def getPageN():
    res = requests.get(‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘)
    res.encoding = ‘utf-8‘
    soup = BeautifulSoup(res.text, ‘html.parser‘)
    n = int(soup.select(‘#pages a‘)[0].text.rstrip(‘条‘))
    return (n // 10 + 1)
    # return n
#将新闻数据结构化为字典的列表:
newsTotal=[]
firstPageUrl=‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘
newsTotal.extend(getListPage(firstPageUrl))
n= getPageN()
for i in range(n,n+1):
    listPageUrl=‘http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html‘.format(i)
    newsTotal.extend(getListPage(listPageUrl))
for news in newsTotal:
  print(news)

import pandas
df = pandas.DataFrame(newstotal)
print(df)

df.to_excel(‘news1.xlsx‘)

print(df[[‘click‘,‘title‘,‘source‘]][:6])
print(df[(df[‘source‘]==‘学校综合办‘)&(df[‘click‘]>3000)])
#使用isin筛选值
sou = [‘国际学院‘,‘学生工作处‘]
df[df[‘source‘].isin(sou)]
print(df[df[‘source‘].isin(sou)])
df1 = df.set_index(‘dt‘)
print(df1[‘2018-03‘])

import sqlite3
with sqlite3.connect(‘gzccnewsdb.sqlite‘) as db:
df3.to_sql(‘gzccnews05‘,con = db, if_exists=‘replace‘)

with sqlite3.connect(‘gzccnewsdb.sqlite‘) as db:
df2 = pandas.read_sql_query(‘SELECT * FROM gzccnews05‘,con=db)
print(df2)

import pymysql
from sqlalchemy import create_engine
conn=create_engine(‘mysql+pymysql://root:@localhost://3306/gzcc?charset=utf8‘)
pandas.io.sql.to_sql(df,‘gzccnews‘,con=conn,if_exists=‘replace‘)