使用正则表达式，取得点击次数，函数抽离

Posted 2020-10-30 127li

用正则表达式进行英文分词。re.split(‘‘,news)

    str = ‘‘‘King Athamus of northern Greece had two children，     Phrixus and Helle．After he left his first wife and mar ried Ino，    a wicked woman，the two children received all the cruel treatment that a stepmother coulddevise ，    At one timethe kingdom was ruined by a famine．‘‘‘
    print(re.split("[\s,.?!]+", str))

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


def getClickCount(newUrl):
    new_id = re.findall(r‘\_(.*).html‘,newUrl)
    new_id = new_id[0].split(‘/‘)[1]
    url = ‘http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80‘.format(new_id)
    content = requests.get(url)
    clickCount = int(re.search("hits‘\).html\(‘(.*)‘\);", content.text).group(1))
    return clickCount

def getNewDetail(newsUrl):

    web=requests.get(newsUrl)
    web.encoding=‘utf-8‘
    soup=BeautifulSoup(web.text, ‘html.parser‘)
    content=soup.find(‘div‘,{‘class‘:‘show-content‘}).text #正文

    list=[]
    info=soup.find(‘div‘,{‘class‘:‘show-info‘})
    info=info.text.replace(‘\xa0‘,‘n‘).split(‘n‘)#细节信息
    for string in info:
        if len(string)>3:
            list.append(string)

    for i in range(len(list)):
        if list[i].find(‘次‘)!=-1:
            list[i]=‘点击:{}次‘.format(getClickCount(newsUrl))

    list.append(content)
    return list

if __name__==‘__main__‘:
    url=‘http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0329/9129.html‘
    new=getNewDetail(url)
    print(new)