使用正则表达式，取得点击次数，函数抽离

Posted 2020-10-30 130-张煌

学会使用正则表达式

1. 用正则表达式判定邮箱是否输入正确。

import re;
def isEmailAccount(str):
    if(re.match("\\w*@\\w*(\\.\\w{2,3}){1,3}$",str)):
        return True
    else:
        return False
print(isEmailAccount(\'[e-mail]\'))
print(isEmailAccount(\'123sdf_sd@qq\'))

2. 用正则表达式识别出全部电话号码。

import re;
import requests
newurl=\'http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0404/9183.html\'
res = requests.get(newurl)
res.encoding=\'utf-8\'
tel=re.findall("(\\d{3,4}) *- *(\\d{7,8})",res.text)
print(tel)

3. 用正则表达式进行英文分词。re.split(\'\',news)

import re;
str="""In this year\'s government work report, Premier Li Keqiang frequently referred to internet-related concepts, like Internet Plus, artificial intelligence, and Digital China, and noted that the Chinese government will give priority to "providing more and better online content"."""
a=re.split(\'[\\s,.?\\" ]+\',str)
print(a)

4. 使用正则表达式取得新闻编号

5. 生成点击次数的Request URL

6. 获取点击次数

import re
import requests
url="http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0404/9183.html"
newId=re.search("/(\\d*).html$",url).group(1)
print(newId)
clickUrl ="http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80".format(newId)
print(clickUrl)
resc = requests.get(clickUrl)
num = re.search(".html\\(\'(\\d*)\'\\)",resc.text).group(1)
print(num)

7. 将456步骤定义成一个函数 def getClickCount(newsUrl):

import re
import requests
def getClickCount(newsUrl):
    newId=re.search("/(\\d*).html$",newsUrl).group(1)
    print(newId)
    clickUrl ="http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80".format(newId)
    print(clickUrl)
    resc = requests.get(clickUrl)
    num = re.search(".html\\(\'(\\d*)\'\\)",resc.text).group(1)
    print(num)
getClickCount("http://news.gzcc.cn/html/2018/xiaoyuanxinwen_0404/9183.html");

8. 将获取新闻详情的代码定义成一个函数 def getNewDetail(newsUrl):

 

import re
import requests
from bs4 import BeautifulSoup
from datetime import datetime
def getClickCount(newsUrl):
    newId=re.search("/(\\d*).html$",newsUrl).group(1)
    print(newId)
    clickUrl ="http://oa.gzcc.cn/api.php?op=count&id={}&modelid=80".format(newId)
    print(clickUrl)
    resc = requests.get(clickUrl)
    num = re.search(".html\\(\'(\\d*)\'\\)",resc.text).group(1)
    print(num)
def getNewDetail(newsUrl):
    res1 = requests.get(newsUrl)
    res1.encoding = \'utf-8\'
    soup1 = BeautifulSoup(res1.text, \'html.parser\')
    # 正文
    content = soup1.select_one("#content").text
    info = soup1.select_one(".show-info").text
    # 发布时间
    time = datetime.strptime(info.lstrip("发布时间:")[:19], "%Y-%m-%d %H:%M:%S")
    # 作者
    author = info[info.find("作者："):].split()[0].lstrip("作者：")
    # 来源
    x = info.find("来源：")
    if x >= 0:
        source = info[x:].split()[0].lstrip("来源：")
    else:
        source = ""
    # 摄影
    x = info.find("摄影：")
    if x >= 0:
        shot = info[x:].split()[0].lstrip("摄影：")
    else:
        shot = ""
    print(title)
    print(url)
    print(content)
    print(time)
    print(author)
    print(source)
    print(shot)
    # 点击次数
    getClickCount(newsUrl);
newsurl=\'http://news.gzcc.cn/html/xiaoyuanxinwen/\'
res = requests.get(newsurl)
res.encoding=\'utf-8\'
soup = BeautifulSoup(res.text,\'html.parser\')
li=soup.select_one(".news-list").select("li")
for i in li:
    #标题
    title=i.select_one(".news-list-title").text
    #链接
    url=i.a.attrs.get(\'href\')
    getNewDetail(url)