获取一篇新闻的全部信息

 

---

给定一篇新闻的链接newsUrl，获取该新闻的全部信息

标题、作者、发布单位、审核、来源

发布时间:转换成datetime类型

点击：

• newsUrl
• newsId(使用正则表达式re)
• clickUrl(str.format(newsId))
• requests.get(clickUrl)
• newClick(用字符串处理，或正则表达式)
• int()

整个过程包装成一个简单清晰的函数。

 

尝试去爬取一个你感兴趣的网页。

import requests
from bs4 import BeautifulSoup
import time
import re

url = 'http://news.gzcc.cn/html/2019/xiaoyuanxinwen_0320/11029.html'


def pross(url):
    parser = 'html.parser'
    res = requests.get(url)
    res.encoding = 'UTF-8'
    soup = BeautifulSoup(res.text, parser)
    for selsoup in soup.select('.show-nav'):
        title = soup.select('.show-title')[0].text  # 标题
        author = soup.select('.show-info')[0].text.split()[2]  # 作者
        inspector = soup.select('.show-info')[0].text.split()[3]  # 审核
        source = soup.select('.show-info')[0].text.split()[4]  # 来源
        content = soup.select('.show-content p')[0].text  # 内容
        newsid = artsid(url)  # 新闻编号id
        time = times(soup)  # 发布时间
        clicktime = artfreq()  # 点击次数
        listt =['标题： '+title,author,inspector,source,'内容：'+content,'ID'+newsid,'时间： '+time,'点击次数： '+clicktime]
        for i in range(8):
            print(listt[i])

def times(soup):
    msg = soup.select('.show-info')[0].text
    msgdate = msg.split()[0].split(':')[1]
    msgtime = msg.split()[1]
    date = msgdate + ' ' + msgtime
    conten1time = time.strftime(date, time.localtime())
    return conten1time


def artsid(url):
    artid = re.match('http://news.gzcc.cn/html/2019/xiaoyuanxinwen_0320/(.*).html', url).group(1)
    return artid


def artfreq():
    clickurl = 'http://oa.gzcc.cn/api.php?op=count&id=11029&modelid=80'
    res = requests.get(clickurl)
    click = res.text.split('.html')[-1].lstrip("('").rstrip("');")
    return click

pross(url)