爬取校园新闻首页的新闻的详情，使用正则表达式，函数抽离

Posted 2020-10-30 157 符致伟

import requests
import re

url = "http://news.gzcc.cn/html/xiaoyuanxinwen/"
res = requests.get(url)
res.encoding = \'utf-8\'

# 利用BeautifulSoup的HTML解析器，生成结构树
from bs4 import BeautifulSoup

soup = BeautifulSoup(res.text, \'html.parser\')


def getClickCount(url):
    HitUrl = \'http://oa.gzcc.cn/api.php?op=count&id=9183&modelid=80\'
    hitNumber = requests.get(HitUrl).text.split(\'.html\')[-1].lstrip("(\'").rstrip("\');")
    print("点击次数:", hitNumber)

    re.match(\'http://news.gzcc.cn/html/2018/xiaoyuanxinwen(.*).html\', url).group(1).split(\'/\')[1]
    print(\'新闻编号:\', re.search(\'\\_(.*).html\', url).group(1))


def getNewDetail(url):
    res = requests.get(url)
    res.encoding = \'utf-8\'
    soup = BeautifulSoup(res.text, \'html.parser\')

    for news in soup.select(\'li\'):
        if len(news.select(\'.news-list-title\')) > 0:
            # 首页文章标题
            title = news.select(\'.news-list-title\')[0].text
            # 首页文章描述
            description = news.select(\'.news-list-description\')[0].text
            # 首页文章信息
            info = news.select(\'.news-list-info\')[0].text
            # 首页文章链接
            href = news.select(\'a\')[0][\'href\']

            url = href
            res = requests.get(url)
            res.encoding = \'utf-8\'
            soup = BeautifulSoup(res.text, \'html.parser\')

            # 获取每篇文章的信息
            newinfo = soup.select(\'.show-info\')[0].text

            # 获取文章内容
            content = soup.select(\'#content\')[0].text

            # 日期
            date = newinfo.split()[0]
            # 当日时间
            time = newinfo.split()[1]
            # 作者
            author = newinfo.split()[2]
            # 审核
            checker = newinfo.split()[3]
            # 来源
            source = newinfo.split()[4]
            # 摄影
            Photography = newinfo.split()[5]

            print(\'------------------------------------------------------------------------------\')
            print("文章标题：" + title)
            print("\\n文章描述：" + description)
            print("\\n文章信息:\\n" + date + \' \' + time + \'\\n\' + author + \'\\n\' + checker + \'\\n\' + source+ \'\\n\' + Photography)
            getClickCount(href)#点击次数、新闻编号
            print("\\n文章链接：" + href)
            print(content)
            print(\'------------------------------------------------------------------------------\')


getNewDetail(url)