python如何获取网络数据

import socket
mysock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
mysock.connect(('fakeserver.com', 80)) # connect to server
cmd = 'GET http://fakeserver.com/fake.txt HTTP/1.0\r\n\r\n'.encode()
# send GET command followed by a blank line
mysock.send(cmd) 

while True: # receive data and print out
    data = mysock.recv(512)
    if (len(data) < 1):
        break
    print(data.decode())
mysock.close()

import urllib.request

fhand = urllib.request.urlopen('http://fakeserver.com/fake.txt')
for line in fhand:
    #convert UTF-8 to unicode string and print out
    print(line.decode().strip()) 

import urllib.request, urllib.parse, urllib.error
from bs4 import BeautifulSoup
import ssl

# Ignore SSL certificate errors
ctx = ssl.create_default_context()
ctx.check_hostname = False
ctx.verify_mode = ssl.CERT_NONE

html = urllib.request.urlopen('http://fakeserver.com/fake.html', context=ctx).read()
soup = BeautifulSoup(html, 'html.parser')
tags = soup('a')
# Retrieve all of the anchor tags
for tag in tags:
    print(tag.get('href', None))

import xml.etree.ElementTree as ET
data =  '''
            <person>
            <name>Jack</name>
            <phone>+123456789</phone>
            <email office="yes"/>
            </person> 
        '''
tree = ET.fromstring(data) # convert xml into a tree
print('Name:', tree.find('name').text)
print('Attr:', tree.find('email').get('office'))

import json
data =  '''
            {
                "name" : "Jack",
                "phone" : {
                    "type" : "intl",
                    "number" : "+123456789"
                },
                "email" : {
                    "office" : "yes"
                }
            }
        '''
info = json.loads(data)  # convert json into a dictianary
print('Name:', info['name'])
print('Attr:', info['email']['office'])