爬取校园网 - 爱码网

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

import requests
from bs4 import BeautifulSoup

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

news = soup.select(\'li\')
for new in news:
    if len(new.select(\'.news-list-title\')) > 0:
        title = new.select(\'.news-list-title\')[0].text  # 标题
        aurl = new.select(\'a\')[0].attrs[\'href\']  # URL
        text = new.select(\'.news-list-description\')[0].text #正文
        print(title+\'\n\'+text+\'\n\'+aurl+\'\n\')

　运行结果：

2. 分析字符串，获取每篇新闻的发布时间，作者，来源，摄影等信息。

res2 = requests.get(aurl)
        res2.encoding = \'utf-8\'
        soup2 = BeautifulSoup(res2.text, \'html.parser\')
        info = soup2.select(\'.show-info\')[0].text
        info = info.lstrip(\'发布时间:\').rstrip(\'点击：次\')
        # print(info)
        time = info[:info.find(\'作者\')] # 发布时间
        author = info[info.find(\'作者：\')+3:info.find(\'审核\')] # 作者
        check = info[info.find(\'审核：\')+3:info.find(\'来源\')]  # 审核
        source = info[info.find("来源：")+3:info.find(\'摄影\')] # 来源
        print(time, author, check, source,end="")
        if(info.find("摄影：")>0):
            photogra = info[info.find("摄影：")+3:] # 摄影
            print(photogra)
        else:
            print()

　运行结果：

3. 将其中的发布时间由str转换成datetime类型。

from datetime import datetime

time = \'2018-04-01 11:57:00\'
formart = datetime.strptime(time, \'%Y-%m-%d %H:%M:%S\')
print(type(formart))
print(formart, formart.strftime(\'%Y/%m/%d\'))

　运行结果：

4. 将完整的代码及运行结果截图发布在作业上。

import requests
from bs4 import BeautifulSoup

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

news = soup.select(\'li\')
for new in news:
    if len(new.select(\'.news-list-title\')) > 0:
        title = new.select(\'.news-list-title\')[0].text  # 标题
        aurl = new.select(\'a\')[0].attrs[\'href\']  # URL
        text = new.select(\'.news-list-description\')[0].text #正文
        print(title + \'\n\' + text + \'\n\' + aurl + \'\n\')

        res2 = requests.get(aurl)
        res2.encoding = \'utf-8\'
        soup2 = BeautifulSoup(res2.text, \'html.parser\')
        info = soup2.select(\'.show-info\')[0].text
        info = info.lstrip(\'发布时间:\').rstrip(\'点击：次\')
        # print(info)
        time = info[:info.find(\'作者\')] # 发布时间
        author = info[info.find(\'作者：\')+3:info.find(\'审核\')] # 作者
        check = info[info.find(\'审核：\')+3:info.find(\'来源\')]  # 审核
        source = info[info.find("来源：")+3:info.find(\'摄影\')] # 来源
        print(time, author, check, source,end="")
        if(info.find("摄影：")>0):
            photogra = info[info.find("摄影：")+3:] # 来源
            print(photogra)
        else:
            print()