py爬取校园网新闻信息

import requests
from bs4 import BeautifulSoup
from datetime import datetime
import re


def gzcc_content_clicks(content_url):
    content_id = re.search('(\d{2,})\.html', content_url).group(1)
    click_url = 'http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(content_id)
    resp = requests.get(click_url)
    resp.encoding = 'utf-8'
    click_number = re.search('\(\'#hits\'\)\.html\(\'(\d+)\'\)', resp.text).group(1)
    return int(click_number)


def gzcc_content_info(content_url):
    content_info = {}
    resp = requests.get(content_url)
    resp.encoding = 'utf-8'
    soup = BeautifulSoup(resp.text, 'html.parser')

    match_str = {'author': '作者：(.*)\s+[审核]?', 'examine': '审核：(.*)\s+[来源]?', 'source': '来源：(.*)\s+[摄影]?', \
                 'photography': '摄影：(.*)\s+[点击]'}
    remarks = soup.select('.show-info')[0].text
    for i in match_str:
        if re.match('.*' + match_str[i], remarks):
            content_info[i] = re.search(match_str[i], remarks).group(1).split("\xa0")[0]
        else:
            content_info[i] = "  "

    time = re.search('\d{4}-\d{2}-\d{2}\s\d{2}:\d{2}:\d{2}', remarks).group()
    content_info['time'] = datetime.strptime(time, '%Y-%m-%d %H:%M:%S')
    content_info['title'] = soup.select('.show-title')[0].text
    content_info['url'] = content_url
    content_info['content'] = soup.select('#content')[0].text

    return content_info


url = 'http://news.gzcc.cn/html/xiaoyuanxinwen/'
res = requests.get(url)
res.encoding = 'utf-8'
soup = BeautifulSoup(res.text, 'html.parser')

news_list = soup.select('.news-list')[0]
news_point = news_list.select('li')
for i in news_point:
    a = i.select('a')[0]['href']
    print(gzcc_content_info(a))
    print(gzcc_content_clicks(a))

　　

转载于:https://www.cnblogs.com/www924121851/p/8707436.html