数据结构化与保存

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


# 获取新闻点击次数
def getnewsclick(url):
    newsId = re.search(r‘\_\d{4}\/(.*).html‘, url).group(1)
    clickUrl = ‘http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80‘.format(newsId)
    clickRes = requests.get(clickUrl)
    # 利用正则表达式获取新闻点击次数
    clickCount = int(re.search("hits‘\).html\(‘(.*)‘\);", clickRes.text).group(1))
    return clickCount


# 获取新闻细节
def getnewsdetail(newsurl):
    resd = requests.get(newsurl)
    resd.encoding = ‘utf-8‘
    soupd = BeautifulSoup(resd.text, ‘html.parser‘)
    newsDict = {}
    content = soupd.select(‘#content‘)[0].text
    info = soupd.select(‘.show-info‘)[0].text
    newsDict[‘title‘] = soupd.select(‘.show-title‘)[0].text
    date = re.search(‘(\d{4}.\d{2}.\d{2}\s\d{2}.\d{2}.\d{2})‘, info).group(1)  # 识别时间格式
    # 识别一个至三个数据
    if info.find(‘作者‘) > 0:
        newsDict[‘author‘] = re.search(‘作者：((.{2,4}\s|.{2,4}、){1,3})‘, info).group(1)
    else:
        newsDict[‘author‘] = ‘none‘
    if info.find(‘审核‘) > 0:
        newsDict[‘check‘] = re.search(‘审核：((.{2,4}\s){1,3})‘, info).group(1)
    else:
        newsDict[‘check‘] = ‘none‘
    if info.find(‘来源‘) > 0:
        first = re.search(‘来源：(.*)\s*点‘, info).group(1)
        if first.find(‘摄影‘) > 0:
            newsDict[‘sources‘] = re.search(‘(.*)\s*摄‘, first).group(1)  # 解决新闻有摄影无法匹配正则的问题
        else:
            newsDict[‘sources‘] = first
    else:
        newsDict[‘sources‘] = ‘none‘
    if info.find(‘摄影‘) > 0:
        newsDict[‘photo‘] = re.search(‘摄影：(.*)\s*点‘, info).group(1)
    else:
        newsDict[‘photo‘] = ‘none‘
    newsDict[‘dateTime‘] = datetime.strptime(date, ‘%Y-%m-%d %H:%M:%S‘)  # 用datetime将时间字符串转换为datetime类型
    newsDict[‘click‘] = getnewsclick(newsurl)  # 调用getnewsclick()获取点击次数
    newsDict[‘content‘] = content
    return newsDict


def getlistpage(listurl):  # 获取一页的新闻，转换成列表返回
    res = requests.get(listurl)
    res.encoding = ‘utf-8‘
    listsoup = BeautifulSoup(res.text, ‘html.parser‘)
    pagelist = []
    for new in listsoup.select(‘.news-list‘)[0].select(‘li‘):
        newsUrl = new.select(‘a‘)[0][‘href‘]
        pagedict = getnewsdetail(newsUrl)  # 调用getnewsdetail()获取新闻详情
        pagelist.append(pagedict)
        # break
    return pagelist


def gettotalpage(listurl):  # 获取总新闻页面
    res = requests.get(listurl)
    res.encoding = ‘utf-8‘
    soup = BeautifulSoup(res.text, ‘html.parser‘)
    return int(soup.select(‘.a1‘)[0].text.rstrip(‘条‘)) // 10 + 1


total = []
listUrl = ‘http://news.gzcc.cn/html/xiaoyuanxinwen/‘
pagelist = getlistpage(listUrl)
total.extend(pagelist)
listCount = gettotalpage(listUrl)
pan = pandas.DataFrame(total)
pan.to_excel(‘result.xlsx‘)  # 导出为Excel表格
pan.to_csv(‘result.csv‘)  # 导出为csv文件
for i in range(2,listCount):
    listUrl= ‘http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html‘.format(i)
    total = getlistpage(listUrl)