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

1. 用requests库和BeautifulSoup库，爬取校园新闻首页新闻的标题、链接、正文、show-info。

2. 分析info字符串，获取每篇新闻的发布时间，作者，来源，摄影等信息。

3. 将字符串格式的发布时间转换成datetime类型

4. 使用正则表达式取得新闻编号

5. 生成点击次数的Request URL

6. 获取点击次数

7. 将456步骤定义成一个函数 def getClickCount(newsUrl):

8. 将获取新闻详情的代码定义成一个函数 def getNewDetail(newsUrl):

9. 尝试用使用正则表达式分析show info字符串，点击次数字符串。

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

def soup1(url):
    req = requests.get(url)
    req.encoding = 'utf-8'
    soup = BeautifulSoup(req.text, 'html.parser')
    return soup


def getNum(urls):
    html_id = list()
    j = 0
    for i in urls:
        html_id.append(re.search('http://news.gzcc.cn/html/2018/xiaoyuanxinwen_(.*).html', i).group(1).split('/')[-1])
        down_url = 'http://oa.gzcc.cn/api.php?op=count&id=' + html_id[j] + '&modelid=80'
        reqd = requests.get(down_url)
        down_num.append(re.search("\('#hits'\).html\('(.*)'\);", reqd.text).group(1))
        j = j + 1
    return down_num


soup = soup1('http://news.gzcc.cn/html/xiaoyuanxinwen')
li_list = soup.select('li')
title = list()
a = list()
for new in li_list:
    if (len(new.select('.news-list-text')) > 0):
        title.append(new.select('.news-list-text')[0].select('.news-list-title')[0].text)
        a.append(new.a.attrs['href'])
info_list = list()
con_list = list()
for curl in a:
    con_soup = soup1(curl)
    con_list.append(con_soup.select('#content')[0].text)
    info_list.append(con_soup.select('.show-info')[0].text.split("\xa0\xa0"))
cs = list()
for i in range(len(con_list)):
    cs.append(''.join(con_list[0]))

down_num = list()
down_num = getNum(a)

for i in range(len(info_list)):
    print('标题：' + title[i])
    print('链接：' + a[i])
    for j in range(len(info_list[i])):
        if (len(info_list[i][j]) > 0 and info_list[i][j] != ' '):
            if (j != len(info_list[i]) - 1):
                print(info_list[i][j])
            else:
                print(info_list[i][j].rstrip('次'), down_num[i], '次')

    print(cs[i])

　　

 

 

转载于:https://www.cnblogs.com/shadows24/p/8762380.html