当前位置 : 主页 > 手机开发 > ROM >

获取一篇新闻的全部信息

来源:互联网 收集:自由互联 发布时间:2021-06-10
import requests from datetime import datetime from bs4 import BeautifulSoup def newsdt(shareinfo): newsDate = shareinfo.split()[0].split( ‘ : ‘ )[1 ] newsTime = shareinfo.split()[1 ] showtime = datetime.strptime(newsDate + " " + newsTim
import requests
from datetime import datetime
from bs4 import BeautifulSoup


def newsdt(shareinfo):
    newsDate = shareinfo.split()[0].split(:)[1]
    newsTime = shareinfo.split()[1]
    showtime = datetime.strptime(newsDate + " " + newsTime, "%Y-%m-%d %H:%M:%S")
    print("新闻发布时间:", end="")
    print(showtime)


click_url = http://oa.gzcc.cn/api.php?op=count&id=11086&modelid=80
def click(click_url):
    return_click_num = requests.get(click_url)
    click_info = BeautifulSoup(return_click_num.text, html.parser)
    click_num = int(click_info.text.split(.html)[3].split("")[1])
    print("点击次数:", end="")
    print(click_num)


html_url = http://news.gzcc.cn/html/2017/xiaoyuanxinwen_0922/8232.html
def anews(html_url):
    resourses = requests.get(html_url)
    resourses.encoding = UTF-8
    soup = BeautifulSoup(resourses.text, html.parser)


    print("\n新闻标题:" + soup.select(.show-title)[0].text)
    publishing_unit = soup.select(.show-info)[0].text.split()[4].split()[1]
    print("新闻发布单位:", end="")
    print(publishing_unit)
    print("作者:", end="")
    writer = soup.select(.show-info)[0].text.split()[2].split()[1]
    print(writer)
    print("新闻内容:" + soup.select(.show-content)[0].text.replace(\u3000, ‘‘))
    shareinfo = soup.select(.show-info)[0].text

    newsdt(shareinfo)
    click(click_url)

anews(html_url)

分享图片

网友评论