urllib基本使用1

urllib不需要下载

# 使用urllib来获取百度首页的源码
import urllib.request

# 1、定义一个url
url = 'http://www.baidu.com'

# 2、模拟浏览器向服务器发送请求
response = urllib.request.urlopen(url)

# 3、获取响应中的页面的源码
# read方法返回的是字节形式的二进制数据
content = response.read().decode('utf-8')

print(content)

# print(type(response))
# HTTPResponse类型

# response.read()
# 一个字节一个字节的读
# response.read(5)
# 一次读5个字节

# response.readline()
# 一次读一行

# response.readlines()
# 一行一行读直至读完

# response.getcode()
# 状态码

# response.geturl()
# 访问的url地址

# response.getheaders()
# 获取响应头

urllib下载

import urllib.request

# 下载网页
url_page = 'http://www.baidu.com'
# url:下载路径，filename文件名字
urllib.request.urlretrieve(url_page,'baidu.html')

# 下载图片
# 下载视频

定制对象

import urllib.request

url = 'https://www.baidu.com'

# url的组成
# http/https  www.baidu.com  80/443                            #
# 协议            主机        端口号       路径      参数      锚点


headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:99.0) Gecko/20100101 Firefox/99.0'
}
request = urllib.request.Request(url=url, headers=headers)
response = urllib.request.urlopen(request)
content = response.read().decode('utf-8')
print(content)

编解码

　　get请求

import urllib.request
import urllib.parse

url = 'https://www.baidu.com/s?wd='
name = urllib.parse.quote("周杰伦")
# 多参数 https://www.baidu.com/s?wd=周杰伦&sex=男
data = {
    'wd': '周杰伦',
    'sex': '男'
}
params = urllib.parse.urlencode(data)
print(params)

　　post请求

import urllib.request
import urllib.parse


url = 'https://fanyi.baidu.com/sug'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:99.0) Gecko/20100101 Firefox/99.0'
}
data = {
    'kw': '蜘蛛'
}
# post请求的参数 必须进行编码（字节码）
data = urllib.parse.urlencode(data).encode("utf-8")

request = urllib.request.Request(url=url, data=data, headers=headers)
response = urllib.request.urlopen(request)
content = response.read().decode('utf-8')
print(content)

　　cookie

import urllib.request
import urllib.parse

url = 'https://fanyi.baidu.com/v2transapi?from=en&to=zh'

headers = {"Accept": "*/*",
           # "Accept-Encoding": "gzip, deflate, br",
           "Accept-Language": "zh-CN,zh;q=0.8,zh-TW;q=0.7,zh-HK;q=0.5,en-US;q=0.3,en;q=0.2",
            "Connection": "keep-alive", "Content-Length": "136",
            "Content-Type": "application/x-www-form-urlencoded; charset=UTF-8",
            "Cookie": "BAIDUID=5157A4D583A89C37A7545DADAB81726C:FG=1; BIDUPSID=36874D3B080FE4D3FE00F130757B1DCB; PSTM=1618275809; __yjs_duid=1_5c8c0adae28380c2c87efcd8b022c3551618281414735; MCITY=-289%3A179%3A; Hm_lvt_64ecd82404c51e03dc91cb9e8c025574=1648619861,1649214103,1649658988,1649730956; REALTIME_TRANS_SWITCH=1; FANYI_WORD_SWITCH=1; HISTORY_SWITCH=1; SOUND_SPD_SWITCH=1; SOUND_PREFER_SWITCH=1; APPGUIDE_10_0_2=1; BDORZ=FFFB88E999055A3F8A630C64834BD6D0; Hm_lpvt_64ecd82404c51e03dc91cb9e8c025574=1649730956; ab_sr=1.0.1_MWVlMDU1ZjZmYWEwNzE5N2UxMzJmMjkwZWQ4Y2U5ZTU3NWQ2NzE1M2YxYWYxYzc3M2Y5NWM5MzQ5YzU2YTRkMTZkNTUyYzQzOWViMjJkMzdiNGQxZjAyNTYxYmRlN2Q5MTcxODg4NDFjYWMxM2I0ZThjZGZmM2YxNTNmNGJlYzNkZDczODgxMzAzMTM1NTlhYTk3ZmYxZGY2ODBkZTMzMw==",
             "Host": "fanyi.baidu.com", "Origin": "https://fanyi.baidu.com", "Referer": "https://fanyi.baidu.com/"
            , "Sec-Fetch-Dest": "empty", "Sec-Fetch-Mode": "cors", "Sec-Fetch-Site": "same-origin"
            , "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:99.0) Gecko/20100101 Firefox/99.0"
            , "X-Requested-With": "XMLHttpRequest"
         }

data = {
    "from": "en",
    "to": "zh",
    "query": "spider",
    "transtype": "realtime",
    "simple_means_flag": "3",
    "sign": "63766.268839",
    "token": "c45b7821850766d1e62222dc6115e145",
    "domain": "common"
}

data = urllib.parse.urlencode(data).encode("utf-8")

request = urllib.request.Request(url=url, data=data, headers=headers)
response = urllib.request.urlopen(request)
content = response.read().decode('utf-8')
print(content)

import json
print(json.loads(content))