代码改变世界

使用正则表达式,取得点击次数,函数抽离

2018-04-09 13:04  129赖锐扬  阅读(172)  评论(0编辑  收藏  举报
import requests
from  bs4 import  BeautifulSoup
from datetime import datetime
import locale
import re
locale.setlocale(locale.LC_CTYPE,'chinese')
newsurl = 'http://news.gzcc.cn/html/xiaoyuanxinwen/'
res = requests.get(newsurl) 
res.encoding = 'utf-8'
soup = BeautifulSoup(res.text,'html.parser')

def getClickCount(newsUrl): 
    newsId = re.findall('\_(.*).html', newsUrl)[0].split('/')[1] 
    clickUrl = 'http://oa.gzcc.cn/api.php?op=count&id=9183&modelid=80'.format(newsId)
    clickStr = requests.get(clickUrl).text
    return(re.search("hits'\).html\('(.*)'\);",clickStr).group(1))

def getNewDetail(newsUrl):  
    resd = requests.get(newsUrl)  
    resd.encoding = 'utf-8'
    soupd = BeautifulSoup(resd.text, 'html.parser')
    print('标题:' + title)
    print('描述:' + description)
    print('链接:' + newsUrl)
    info = soupd.select('.show-info')[0].text
    time = re.search('发布时间:(.*) \xa0\xa0 \xa0\xa0作者:', info).group(1)
    dtime = datetime.strptime(time, '%Y-%m-%d %H:%M:%S')  
    print('发布时间:{}'.format(dtime))
    print('作者:' + re.search('作者:(.*)审核:', info).group(1))
    print('审核:' + re.search('审核:(.*)来源:', info).group(1))
    print('来源:' + re.search('来源:(.*)摄影:', info).group(1))
    print('摄影:' + re.search('摄影:(.*)点击', info).group(1))
    print('点击次数:' + getClickCount(a))
    print('正文:'+soupd.select('.show-content')[0].text)

for news in soup.select('li'):
    if len(news.select('.news-list-title'))>0:
        title = news.select('.news-list-title')[0].text
        description = news.select('.news-list-description')[0].text
        a = news.a.attrs['href']
        getNewDetail(a)
        break