使用正则表达式，取得点击次数，函数抽离

Posted 2020-10-30 089-袁佳鹏

# -*- coding: utf-8 -*-
import requests
import re
from bs4 import BeautifulSoup
from datetime import datetime

# 7. 将456步骤定义成一个函数 def getClickCount(newsUrl):
def getClickCount(newsUrl):
    # 4. 使用正则表达式取得新闻编号
    # url = "http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0404/9183.html"
    num = ".*/(.*).html"
    num2 = re.match(num, newsUrl)
    if num2:
        print(num2.group(1))

    # 5. 生成点击次数的Request URL
    newsId = re.search(\'\\_(.*).html\', newsUrl).group(1).split(\'/\')[-1]
    clickUrl = \'http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80\'.format(newsId)
    print(clickUrl)

    # 6. 获取点击次数
    resc = requests.get(clickUrl)
    a = resc.text.split(\'.html\')[-1].lstrip("(\'").rstrip("\');")
    print(a)

# 8. 将获取新闻详情的代码定义成一个函数 def getNewDetail(newsUrl):
def getNewDetail(newsUrl):
    res1 = requests.get(newsUrl)
    res1.encoding = "utf-8"
    soup = BeautifulSoup(res1.text, "html.parser")
    con = soup.select(\'#content\')[0].tedtxt
    info = soup.select(\'.show-info\')[0].text
    dt = info.lstrip(\'发布时间:\')[:19]
    # str = \'2018-03-30 17:10:12\'
    dt2 = datetime.strptime(dt, \'%Y-%m-%d %H:%M:%S\')
    print(dt2)

    i = info.find(\'来源：\')
    if i > 0:
        s = info[info.find(\'来源：\'):].split()[0].lstrip(\'来源：\')
        print(s)
    a = info.find(\'作者：\')
    if a > 0:
        l = info[info.find(\'作者：\'):].split()[0].lstrip(\'作者：\')
        print(l)
    y = info.find(\'摄影：\')
    if y > 0:
        u = info[info.find(\'作者：\'):].split()[0].lstrip(\'作者：\')






# 1. 用正则表达式判定邮箱是否输入正确。
r = \'^(\\w)+([.\\_\\-]\\w+)*@(\\w)+((\\.\\w{2,3}){1,3})$\'
e = \'[e-mail]\'
if re.match(r,e):
    print("success")
else:
    print("fail")

#     2. 用正则表达式识别出全部电话号码。
str = "\'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：[phone]\'"
phone = re.findall(\'(\\d{3,4})-(\\d{6,8})\',str)
print(phone)

# 3. 用正则表达式进行英文分词。re.split(\'\',news)
cons = "\'Everyone has their own dreams, I am the same. But my dream is not a lawyer, not a doctor, not actors, not even an industry. Perhaps my dream big people will find it ridiculous, but this has been my pursuit! My dream is to want to have a folk life! I want it to become a beautiful painting, it is not only sharp colors, but also the colors are bleak, I do not rule out the painting is part of the black, but I will treasure these bleak colors! Not yet, how about, a colorful painting, if not bleak, add color, how can it more prominent American? Life is like painting, painting the bright red color represents life beautiful happy moments.\'"
con = re.split("[\\s,.?\\\' ]+",cons)
print(con)

res = requests.get(\'http://news.gzcc.cn/html/xiaoyuanxinwen/\')
res.encoding = \'utf-8\'
soup = BeautifulSoup(res.text,\'html.parser\')
for news in soup.select(\'li\'):
    if len(news.select(\'.news-list-title\'))>0:
        href = news.select(\'a\')[0].attrs[\'href\']
        getClickCount(href)
        getNewDetail(href)
        break