Python网络编程

socket

import socket

# 规定socket使用http和sock stream
mysock = 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bytes
cmd = '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 urlopen

url = '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 API
serviceurl = '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 json
from urllib.request import  urlopen

hfile = urlopen('http://py4e-data.dr-chuck.net/comments_56196.json')
data = hfile.read()
data = json.loads(data)

sum = 0
for item in data['comments']:
    sum += int(item['count'])
print(sum)