Python网络编程

socket

import socket# 规定socket使用http和sock streammysock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)# 链接到指定url和端口mysock.connect(('data.pr4e.org', 80))# encode将utf-8转换为bytescmd = 'GET http://data.pr4e.org/romeo.txt HTTP/1.0\r\n\r\n'.encode()# 向服务器发送请求mysock.send(cmd)while True:    data = mysock.recv(20)    if (len(data) < 1):        break    # decode将bytes转换为utf-8    print(data.decode(),end='')mysock.close()

urlopen

from urllib.request import urlopenurl = 'http://py4e-data.dr-chuck.net/comments_56193.html'# 读取全部回复html = urlopen(url).read()print(html)

解析Tag数据

html = urllib.request.urlopen(url).read()# html是服务器返回的全部内容soup = BeautifulSoup(html, 'html.parser')# 选取所有<a></a>tags = soup('a')for tag in tags:    # 读取<a href="">的内容     print(tag.get('href', None))

import json# Note that Google is increasingly requiring keys# for this APIserviceurl = 'http://py4e-data.dr-chuck.net/geojson?'while True:    address = 'Universidade do Minho'    if len(address) < 1: break    url = serviceurl + urllib.parse.urlencode(        {'address': address})    print('Retrieving', url)    uh = urllib.request.urlopen(url)    data = uh.read().decode()

import jsonfrom urllib.request import  urlopenhfile = urlopen('http://py4e-data.dr-chuck.net/comments_56196.json')data = hfile.read()data = json.loads(data)sum = 0for item in data['comments']:    sum += int(item['count'])print(sum)