获取全部校园新闻

import requests
from  bs4 import  BeautifulSoup
from datetime import datetime
import locale
import re
locale.setlocale(locale.LC_CTYPE,'chinese')

def getClickCount(newsUrl):
    newsId = re.findall('\_(.*).html', newsUrl)[0].split('/')[1]   #使用正则表达式取得新闻编号
    clickUrl = 'http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(newsId)
    clickStr = requests.get(clickUrl).text
    return(re.search("hits'\).html\('(.*)'\);",clickStr).group(1))

def getNewDetail(newsUrl):
    resd = requests.get(newsUrl)  # 返回response
    resd.encoding = 'utf-8'
    soupd = BeautifulSoup(resd.text, 'html.parser')
    print('标题:' + soupd.select('.show-title')[0].text)
    # print('描述:' + soupd.select('.show-description')[0].text)
    print('链接:' + newsUrl)
    info = soupd.select('.show-info')[0].text
    time = re.search('发布时间:(.*) \xa0\xa0 \xa0\xa0作者:', info).group(1)
    dtime = datetime.strptime(time, '%Y-%m-%d %H:%M:%S')
    print('发布时间:{}'.format(dtime))
    print('作者:' + re.search('作者:(.*)审核:', info).group(1))
    # print('审核:' + re.search('审核:(.*)来源:', info).group(1))
    # print('来源:' + re.search('来源:(.*)摄影:', info).group(1))
    # print('摄影:' + re.search('摄影:(.*)点击', info).group(1))
    clickCount = getClickCount(newsUrl)
    print('点击次数:' + clickCount)
    # print(soupd.select('.show-content')[0].text)

def getListPage(ListPageUrl):
    res = requests.get(ListPageUrl)
    res.encoding = 'utf-8'
    soup = BeautifulSoup(res.text,'html.parser')
    # print(soup.select('li'))
    for news in soup.select('li'):
        if len(news.select('.news-list-title'))>0:
            a = news.a.attrs['href']
            getNewDetail(a)

firstUrl = 'http://news.gzcc.cn/html/xiaoyuanxinwen/'
print('第1页:')
getListPage(firstUrl)
res = requests.get(firstUrl)
res.encoding = 'utf-8'
soupn = BeautifulSoup(res.text,'html.parser')
n =  int(soupn.select('.a1')[0].text.rstrip(''))//10+1

for i in range(2,n):
    pageUrl = 'http://news.gzcc.cn/html/xiaoyuanxinwen/{}.html'.format(i)
    print('第{}页:'.format(i))
    getListPage(pageUrl)
    break
import requests
from bs4 import BeautifulSoup
def getHTMLText(url):
    try:
        r = requests.get(url, timeout = 30)
        r.raise_for_status()
        return r.text
    except:
        return ""
def getContent(url):
    html = getHTMLText(url)
    soup = BeautifulSoup(html, "html.parser")
    title = soup.select("div.hd > h1")
    print(title[0].get_text())
    time = soup.select("div.a_Info > span.a_time")
    print(time[0].string)
    author = soup.select("div.qq_articleFt > div.qq_toolWrap > div.qq_editor")
    print(author[0].get_text())
    paras = soup.select("div.Cnt-Main-Article-QQ > p.text")
    for para in paras:
        if len(para) > 0:
            print(para.get_text())
            print()
    #写入文件
    fo = open("text.txt", "w+")
    fo.writelines(title[0].get_text() + "\n")
    fo.writelines(time[0].get_text() + "\n")
    for para in paras:
        if len(para) > 0:
            fo.writelines(para.get_text() + "\n\n")
    fo.writelines(author[0].get_text() + '\n')
    fo.close()
    article = {
        'Title' : title[0].get_text(),
        'Time' : time[0].get_text(),
        'Paragraph' : paras,
        'Author' : author[0].get_text()
    }
    print(article)
def main():
    url = "http://news.qq.com/a/20170504/012032.htm"
    getContent(url);
main()

 

posted @ 2018-04-11 21:57  186-叶晓钿  阅读(156)  评论(0编辑  收藏  举报