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(补)

import requests
from bs4 import BeautifulSoup
from datetime import datetime
import re
res = requests.get('http://news.gzcc.cn/html/xiaoyuanxinwen/')
res.encoding = 'utf-8'
soup = BeautifulSoup(res.text, 'html.parser')


# 获取新闻点击次数
def getNewsId(url):
newsId = re.findall(r'\_(.*).html', url)[0][-4:]
clickUrl = 'http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(newsId)
clickRes = requests.get(clickUrl)
# 利用正则表达式获取新闻点击次数
clickCount = int(re.search("hits'\).html\('(.*)'\);", clickRes.text).group(1))
return clickCount

def getNewDetail(newsUrl):
# 读取新闻细节
resDescript = requests.get(newsUrl)
resDescript.encoding = "utf-8"
soupDescript = BeautifulSoup(resDescript.text, 'html.parser')

content = soupDescript.select(".show-content")[0].text # 正文
info = soupDescript.select(".show-info")[0].text # info相关内容
# 第一种方法 分离 message = info.split()
# 第二种方法 用正则表达式
time = re.search("发布时间:(.*) \xa0\xa0 \xa0\xa0作者:", info).group(1)
author = re.search("作者:(.*)\xa0\xa0审核:", info).group(1)
right = re.search("审核:(.*)\xa0\xa0来源:", info).group(1)
resource = re.search('来源:(.*)\xa0\xa0\xa0\xa0摄影:', info).group(1)
video = re.search("摄影:(.*)\xa0\xa0\xa0\xa0点击:", info).group(1)
count = getNewsId(newsUrl)
dateTime = datetime.strptime(time, '%Y-%m-%d %H:%M:%S')

print('标题' + ': ' + title)
print('概要' + ': ' + description)
print('链接' + ': ' + a)
print('正文' + ' :' + content)
print('发布时间:{0}\n作者:{1}\n审核:{2}\n来源:{3}\n摄影:{4}\n点击次数:{5}'.format(dateTime, author, right, resource, video,count))
print("\n")

for s in soup.select("li"):
if len(s.select(".news-list-title"))>0:
title = s.select(".news-list-title")[0].text #新闻标题
description = s.select(".news-list-description")[0].text #新闻描述
a = s.a.attrs["href"] #观看新闻细节
getNewDetail(a)

猜你喜欢

转载自www.cnblogs.com/huangzemian123/p/9147863.html