Python简易爬虫

服务端代码：

from flask import Flask,request
import os

app= Flask(__name__)
@app.route("/")
def show():
    if os.path.exists("students.txt"):
        st="<h3>学生信息表</h3>"
        st=st+"<table border='1' width='300'>"
        fobj=open("students.txt","rt")  # encoding="utf-8"
        while True:
            #读取一行,去除行尾部"\n"换行符号
            s=fobj.readline().strip("\n")
            #如果读到文件尾部就退出
            if s=="":
                break
            #按逗号拆分开
            s=s.split(",")
            st=st+ "<tr>"
            #把各个数据组织在<td> ... </td>的单元中
            for i in range(len(s)):
                st=st+"<td>"+s[i]+"</td>"
            #完成一行
            st=st+"</tr>"
        fobj.close()
        st=st+"</table>"
        return st
if __name__== "__main__":
    app.run()

客户端代码：

import urllib.request
import re
try:
    resp = urllib.request.urlopen("http://127.0.0.1:5000")
    data = resp.read()
    html = data.decode()
    print(html)
    m = re.search(r"<tr>",html)
    n = re.search(r"</tr>", html)
    while m!= None and n!= None:
        row = html[m.end():n.start()]
        a = re.search(r"<td>", row)
        b = re.search(r"</td>", row)
        while a != None and b != None:
            s = row[a.end():b.start()]
            print(s, end=" ")
            row = row[b.end():]
            a = re.search(r"<td>", row)
            b = re.search(r"</td>", row)
        print()
        html = html[n.end():]
        m = re.search(r"<tr>", html)
        n = re.search(r"</tr>", html)
except Exception as e:
    print(e)

students.txt内容：

No,Name,Gender,Age
1001,张三,男,20
1002,李四,女,19
1003,王五,男,21

客户端代码说明：