爬虫新练习

import requests
import re
from bs4 import BeautifulSoup

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

url1="http://oa.gzcc.cn/api.php?op=count&id=9183&modelid=80"
res1=requests.get(url1)
print(res1.text.split(".html")[-1].lstrip("('").rstrip("');"))

newUrl ='http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0404/9183.html'
re1 = re.search('\_(.*).html',newUrl)
re2 = re.match('http://news.gzcc.cn/html/2018/xiaoyuanxinwen_(.*).html',newUrl)
print(re1.group(1).split('/')[-1],re2.group(1).split('/')[-1])

以上的上节课的练习

 1. 用正则表达式判定邮箱是否输入正确。

e='916843392qq.com'
r='^(\w)+([\.\_\-]\w+)*@(\w)+((\.\w{2,3}){1,3})$'
print(re.match(r,e))

 

2. 用正则表达式识别出全部电话号码。

tel='版权所有：广州商学院   地址：广州市黄埔区九龙大道206号  学校办公室：020-82876130  招生电话：020-82872773'
a=re.search('(\d{3,4})-(\d{6,8})',tel).group(2)
print(a)

3. 用正则表达式进行英文分词。re.split('',news)

str='''Lee is on a five-day working visit to China starting Sunday, his second visit to China since September. During the visit, he will attend the Boao Forum for Asia's annual conference in Hainan. It will be his first time at the conference and he will deliver a speech at the opening session of the forum.'''
print(re.split("[\s,.?!]+",str))

4. 使用正则表达式取得新闻编号

q='http://news.gzcc.cn/html/2017/xiaoyuanxinwen_0925/8249.html'
print(re.match('http://news.gzcc.cn/html/2017/xiaoyuanxinwen_(.*).html',q).group(1).split('/')[-1])
print(re.search('\_(.*).html',q).group(1).split('/')[-1])
print(re.findall('\_(.*).html',q)[-1].split('/')[-1])

 

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):

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

def getClickCount(newUrl):
    newId=re.search('\_(.*).html',newUrl).group(1).split('/')[1]
    clickUrl='http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(newId)
    return (int(requests.get(clickUrl).text.split('.html')[-1].lstrip("('").rstrip("');")))
def getNewDetail(url):
    res1 = requests.get(a)
    res1.encoding = 'utf-8'
    soup1 = BeautifulSoup(res1.text, 'html.parser')

    soup1.select('#content')[0].text  # 正文
    info = soup1.select('.show-info')[0].text
    d = info.lstrip('发布时间:')[:19] #发布日期和时间

    dt=datetime.strptime(d,'%Y-%m-%d %H:%M:%S')
    au=info[info.find('作者：'):].split()[0].lstrip('作者：') #作者
    clickCount=getClickCount(a)

newUrl="http://news.gzcc.cn/html/2017/xiaoyuanxinwen_0925/8249.html"
newId = re.search('\_(.*).html', newUrl).group(1).split('/')[1]
clickUrl = 'http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80'.format(newId)
print(clickUrl,'\n',getClickCount(newUrl))

url='http://news.gzcc.cn/html/xiaoyuanxinwen/'
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:
        t=news.select('.news-list-title')[0].text
        a = news.select('a')[0].attrs['href']  # 新闻链接
        print(t,a,'\n')
        getNewDetail(a)
        break