复工复产，利用Python爬虫爬取火车票信息

Python 爬虫操作基本操作

python 标准库 urllib

获取信息

import urllib.request

response = urllib.request.urlopen('http://www.baidu.com/')

print(response.read().decode('utf-8'))

此处省略
        
    

            
    
        
	

上传信息

import urllib.request
import urllib.parse

data = bytes(urllib.parse.urlencode({'word':'hello'}), encoding='utf-8')

response = urllib.request.urlopen('http://httpbin.org/post', data=data)
response
html = response.read().decode('utf-8')
print(html)

{
  "args": {}, 
  "data": "", 
  "files": {}, 
  "form": {
    "word": "hello"
  }, 
  "headers": {
    "Accept-Encoding": "identity", 
    "Content-Length": "10", 
    "Content-Type": "application/x-www-form-urlencoded", 
    "Host": "httpbin.org", 
    "User-Agent": "Python-urllib/3.6", 
    "X-Amzn-Trace-Id": "Root=1-5ec0a4a4-4da16208bf73bce8b0088a14"
  }, 
  "json": null, 
  "origin": "182.137.240.188", 
  "url": "http://httpbin.org/post"
}

python 标准库 urllib3

获取信息

import urllib3

# 处理与线程的连接以及线程安全
http = urllib3.PoolManager()
response = http.request('GET', 'http://www.baidu.com')

print(response.data.decode())

	
	
	
	
	
	
	
	
	
	
	
	
    此处省略

上传信息

import urllib3

# 处理与线程的连接以及线程安全
http = urllib3.PoolManager()
response = http.request('POST', 'http://httpbin.org/post', fields={'word':'hello'})

print(response.data.decode())

{
  "args": {}, 
  "data": "", 
  "files": {}, 
  "form": {
    "word": "hello"
  }, 
  "headers": {
    "Accept-Encoding": "identity", 
    "Content-Length": "128", 
    "Content-Type": "multipart/form-data; boundary=14c9abc7c138e04cfb65714db9055b19", 
    "Host": "httpbin.org", 
    "X-Amzn-Trace-Id": "Root=1-5ec0a5af-6146cbc0386719987392e77c"
  }, 
  "json": null, 
  "origin": "182.137.240.188", 
  "url": "http://httpbin.org/post"
}

第三方库 requests

获取特征信息

import requests

response = requests.get('http://www.baidu.com/')

# 防止中文乱码
response.encoding='utf-8'

print('状态码\n', response.status_code)
print('请求地址\n', response.url)
print('头部信息\n', response.headers)
print('Cookie\n', response.cookies)
print('文本源码\n', response.text)
print('字节源码\n', response.content)

状态码
 200
请求地址
 http://www.baidu.com/
头部信息
 {'Cache-Control': 'private, no-cache, no-store, proxy-revalidate, no-transform', 'Content-Encoding': 'gzip', 'Content-Type': 'text/html', 'Date': 'Sun, 17 May 2020 02:55:45 GMT', 'Last-Modified': 'Mon, 23 Jan 2017 13:27:56 GMT', 'Pragma': 'no-cache', 'Server': 'bfe/1.0.8.18', 'Set-Cookie': 'BDORZ=27315; max-age=86400; domain=.baidu.com; path=/', 'Connection': 'close', 'Transfer-Encoding': 'chunked'}
Cookie
 ]>
文本源码
 
  
 

字节源码 b'\r\n ......