python网络爬虫之Urllib

概述

urllib的request模块提供了最基本的构造HTTP请求的方法，使用它可以方便地实现请求的发送并得到响应，同时它还带有处理授权验证（authentication）、重定向（redirection）、浏览器Cookies以及其他内容。

urllib包的基本使用方法

# 引用urllib包里面request类
import urllib.request


# todo (1)定义一个url  就是你要访问的地址
url = 'http://www.baidu.com'

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

# todo （3）获取响应中的页面的源码  content 内容的意思
# read方法  返回的是字节形式的二进制数据
# 我们要将二进制的数据转换为字符串
# 二进制--》字符串  解码  decode('编码的格式')
content = response.read().decode('utf-8')

# todo（4）打印数据
print(content)

urllib的一个类型和六个方法

import urllib.request

# todo 请求地址
url = 'http://www.baidu.com'

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

# 一个类型和六个方法
print("response是HTTPResponse的类型")
print(type(response))

# 按照一个字节一个字节的去读
print("按照一个字节一个字节的去读")
content = response.read()
print(content)

# 返回多少个字节
print("返回多少个字节")
content = response.read(5)
print(content)

# 读取一行
print("读取一行")
content = response.readline()
print(content)

print("读取所有行")
content = response.readlines()
print(content)

# 返回状态码  如果是200了 那么就证明我们的逻辑没有错
print("返回状态码  如果是200了 那么就证明我们的逻辑没有错")
print(response.getcode())

# 返回的是url地址
print("返回的是url地址")
print(response.geturl())

# 获取是一个状态信息
print(response.getheaders())

# 一个类型 HTTPResponse
# 六个方法 read  readline  readlines  getcode geturl getheaders

urllib下载的方法

import urllib.request

# 下载网页
print("下载网页")
url_page = 'http://www.baidu.com'
# url代表的是下载的路径  filename文件的名字
# 在python中 可以变量的名字  也可以直接写值
urllib.request.urlretrieve(url_page,'baidu.html')

# 下载图片
print("下载图片")
url_img = 'https://img1.baidu.com/it/u=3004965690,4089234593&fm=26&fmt=auto&gp=0.jpg'
urllib.request.urlretrieve(url= url_img,filename='lisa.jpg')

# 下载视频
print("下载视频")
url_video = 'https://vd3.bdstatic.com/mda-mhkku4ndaka5etk3/1080p/cae_h264/1629557146541497769/mda-mhkku4ndaka5etk3.mp4?v_from_s=hkapp-haokan-tucheng&auth_key=1629687514-0-0-7ed57ed7d1168bb1f06d18a4ea214300&bcevod_channel=searchbox_feed&pd=1&pt=3&abtest='
urllib.request.urlretrieve(url_video,'hxekyyds.mp4')

urllib请求对象

# todo 引入包
import urllib.request

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

# url的组成
# https://www.baidu.com/s?wd=周杰伦

# http/https    www.baidu.com   80/443     s      wd = 周杰伦     #
#    协议             主机        端口号     路径     参数           锚点
# http   80
# https  443
# mysql  3306
# oracle 1521
# redis  6379
# mongodb 27017

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36'
}

# 因为urlopen方法中不能存储字典 所以headers不能传递进去
# 请求对象的定制
request = urllib.request.Request(url=url, headers=headers)
# 调用请求
response = urllib.request.urlopen(request)
# 设置编码格式
content = response.read().decode('utf8')
# 输出内容
print(content)

urllib_get请求的quote方法

# https://www.baidu.com/s?wd=%E5%91%A8%E6%9D%B0%E4%BC%A6
# 需求 获取 https://www.baidu.com/s?wd=周杰伦的网页源码
# todo urlencode应用场景：一个参数的时候

import urllib.request
import urllib.parse


url = 'https://www.baidu.com/s?wd='

# 请求对象的定制为了解决反爬的第一种手段
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36'
}

# 将周杰伦三个字变成unicode编码的格式
# 我们需要依赖于urllib.parse
name = urllib.parse.quote('周杰伦')

url = url + name

# 请求对象的定制
request = urllib.request.Request(url=url,headers=headers)

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

# 获取响应的内容
content = response.read().decode('utf-8')

# 打印数据
print(content)

urllib_get请求的urlencode方法

# todo urlencode应用场景：多个参数的时候
# https://www.baidu.com/s?wd=周杰伦&sex=男
#获取https://www.baidu.com/s?wd=%E5%91%A8%E6%9D%B0%E4%BC%A6&sex=%E7%94%B7的网页源码

import urllib.request
import urllib.parse

base_url = 'https://www.baidu.com/s?'

data = {
    'wd':'周杰伦',
    'sex':'男',
    'location':'中国台湾省'
}

new_data = urllib.parse.urlencode(data)

# 请求资源路径
url = base_url + new_data

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36'
}

# 请求对象的定制
request = urllib.request.Request(url=url,headers=headers)

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

# 获取网页源码的数据
content = response.read().decode('utf-8')

# 打印数据
print(content)

urllib_post请求

# 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) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36'
}

data = {
    'kw':'spider'
}

# post请求的参数 必须要进行编码
data = urllib.parse.urlencode(data).encode('utf-8')

# post的请求的参数 是不会拼接在url的后面的  而是需要放在请求对象定制的参数中
# post请求的参数 必须要进行编码
request = urllib.request.Request(url=url,data=data,headers=headers)

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

# 获取响应的数据
content = response.read().decode('utf-8')

# 字符串--》json对象

import json

obj = json.loads(content)
print(obj)



# post请求方式的参数 必须编码   data = urllib.parse.urlencode(data)
# 编码之后 必须调用encode方法 data = urllib.parse.urlencode(data).encode('utf-8')
# 参数是放在请求对象定制的方法中  request = urllib.request.Request(url=url,data=data,headers=headers)

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=0.9',
    # 'Connection': 'keep-alive',
    # 'Content-Length': '135',
    # 'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',
    'Cookie': 'BIDUPSID=DAA8F9F0BD801A2929D96D69CF7EBF50; PSTM=1597202227; BAIDUID=DAA8F9F0BD801A29B2813502000BF8E9:SL=0:NR=10:FG=1; __yjs_duid=1_c19765bd685fa6fa12c2853fc392f8db1618999058029; REALTIME_TRANS_SWITCH=1; FANYI_WORD_SWITCH=1; HISTORY_SWITCH=1; SOUND_SPD_SWITCH=1; SOUND_PREFER_SWITCH=1; BDUSS=R2bEZvTjFCNHQxdUV-cTZ-MzZrSGxhbUYwSkRkUWk2SkxxS3E2M2lqaFRLUlJoRVFBQUFBJCQAAAAAAAAAAAEAAAA3e~BTveK-9sHLZGF5AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAFOc7GBTnOxgaW; BDUSS_BFESS=R2bEZvTjFCNHQxdUV-cTZ-MzZrSGxhbUYwSkRkUWk2SkxxS3E2M2lqaFRLUlJoRVFBQUFBJCQAAAAAAAAAAAEAAAA3e~BTveK-9sHLZGF5AAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAFOc7GBTnOxgaW; BDORZ=B490B5EBF6F3CD402E515D22BCDA1598; BAIDUID_BFESS=DAA8F9F0BD801A29B2813502000BF8E9:SL=0:NR=10:FG=1; BDRCVFR[feWj1Vr5u3D]=I67x6TjHwwYf0; PSINO=2; H_PS_PSSID=34435_31660_34405_34004_34073_34092_26350_34426_34323_22158_34390; delPer=1; BA_HECTOR=8185a12020018421b61gi6ka20q; BCLID=10943521300863382545; BDSFRCVID=boDOJexroG0YyvRHKn7hh7zlD_weG7bTDYLEOwXPsp3LGJLVJeC6EG0Pts1-dEu-EHtdogKK0mOTHv8F_2uxOjjg8UtVJeC6EG0Ptf8g0M5; H_BDCLCKID_SF=tR3aQ5rtKRTffjrnhPF3-44vXP6-hnjy3bRkX4Q4Wpv_Mnndjn6SQh4Wbttf5q3RymJ42-39LPO2hpRjyxv4y4Ldj4oxJpOJ-bCL0p5aHl51fbbvbURvD-ug3-7qqU5dtjTO2bc_5KnlfMQ_bf--QfbQ0hOhqP-jBRIE3-oJqC8hMIt43f; BCLID_BFESS=10943521300863382545; BDSFRCVID_BFESS=boDOJexroG0YyvRHKn7hh7zlD_weG7bTDYLEOwXPsp3LGJLVJeC6EG0Pts1-dEu-EHtdogKK0mOTHv8F_2uxOjjg8UtVJeC6EG0Ptf8g0M5; H_BDCLCKID_SF_BFESS=tR3aQ5rtKRTffjrnhPF3-44vXP6-hnjy3bRkX4Q4Wpv_Mnndjn6SQh4Wbttf5q3RymJ42-39LPO2hpRjyxv4y4Ldj4oxJpOJ-bCL0p5aHl51fbbvbURvD-ug3-7qqU5dtjTO2bc_5KnlfMQ_bf--QfbQ0hOhqP-jBRIE3-oJqC8hMIt43f; Hm_lvt_64ecd82404c51e03dc91cb9e8c025574=1629701482,1629702031,1629702343,1629704515; Hm_lpvt_64ecd82404c51e03dc91cb9e8c025574=1629704515; __yjs_st=2_MDBkZDdkNzg4YzYyZGU2NTM5NzBjZmQ0OTZiMWRmZGUxM2QwYzkwZTc2NTZmMmIxNDJkYzk4NzU1ZDUzN2U3Yjc4ZTJmYjE1YTUzMTljYWFkMWUwYmVmZGEzNmZjN2FlY2M3NDAzOThhZTY5NzI0MjVkMmQ0NWU3MWE1YTJmNGE5NDBhYjVlOWY3MTFiMWNjYTVhYWI0YThlMDVjODBkNWU2NjMwMzY2MjFhZDNkMzVhNGMzMGZkMWY2NjU5YzkxMDk3NTEzODJiZWUyMjEyYTk5YzY4ODUyYzNjZTJjMGM5MzhhMWE5YjU3NTM3NWZiOWQxNmU3MDVkODExYzFjN183XzliY2RhYjgz; ab_sr=1.0.1_ZTc2ZDFkMTU5ZTM0ZTM4MWVlNDU2MGEzYTM4MzZiY2I2MDIxNzY1Nzc1OWZjZGNiZWRhYjU5ZjYwZmNjMTE2ZjIzNmQxMTdiMzIzYTgzZjVjMTY0ZjM1YjMwZTdjMjhiNDRmN2QzMjMwNWRhZmUxYTJjZjZhNTViMGM2ODFlYjE5YTlmMWRjZDAwZGFmMDY4ZTFlNGJiZjU5YzE1MGIxN2FiYTU3NDgzZmI4MDdhMDM5NTQ0MjQxNDBiNzdhMDdl',
    # 'Host': 'fanyi.baidu.com',
    # 'Origin': 'https://fanyi.baidu.com',
    # 'Referer': 'https://fanyi.baidu.com/?aldtype=16047',
    # 'sec-ch-ua': '"Chromium";v="92", " Not A;Brand";v="99", "Google Chrome";v="92"',
    # 'sec-ch-ua-mobile': '?0',
    # 'Sec-Fetch-Dest': 'empty',
    # 'Sec-Fetch-Mode': 'cors',
    # 'Sec-Fetch-Site': 'same-origin',
    # 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36',
    # 'X-Requested-With': 'XMLHttpRequest',
}

data = {
    'from': 'en',
    'to': 'zh',
    'query': 'love',
    'transtype': 'realtime',
    'simple_means_flag': '3',
    'sign': '198772.518981',
    'token': '5483bfa652979b41f9c90d91f3de875d',
    'domain': 'common',
}
# post请求的参数  必须进行编码 并且要调用encode方法
data = urllib.parse.urlencode(data).encode('utf-8')

# 请求对象的定制
request = urllib.request.Request(url = url,data = data,headers = headers)

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

# 获取响应的数据
content = response.read().decode('utf-8')

import json

obj = json.loads(content)
print(obj)

通过urllib_get请求获取db电影的第一页的数据保存

# get请求
# 获取豆瓣电影的第一页的数据 并且保存起来

import urllib.request

url = 'https://movie.douban.com/j/chart/top_list?type=5&interval_id=100%3A90&action=&start=0&limit=20'

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36'
}

# (1) 请求对象的定制
request = urllib.request.Request(url=url,headers=headers)

# （2）获取响应的数据
response = urllib.request.urlopen(request)
content = response.read().decode('utf-8')

# (3) 数据下载到本地
# open方法默认情况下使用的是gbk的编码  如果我们要想保存汉字 那么需要在open方法中指定编码格式为utf-8
# encoding = 'utf-8'
fp = open('douban.json','w',encoding='utf-8')
fp.write(content)

通过urllib_post请求获取kdj官网

# 1页
# http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?op=cname
# post
# cname: 北京
# pid:
# pageIndex: 1
# pageSize: 10


# 2页
# http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?op=cname
# post
# cname: 北京
# pid:
# pageIndex: 2
# pageSize: 10

import urllib.request
import urllib.parse

def create_request(page):
    base_url = 'http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?op=cname'

    data = {
        'cname': '北京',
        'pid':'',
        'pageIndex': page,
        'pageSize': '10'
    }

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

    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36'
    }

    request = urllib.request.Request(url=base_url,headers=headers,data=data)

    return request

def get_content(request):
    response = urllib.request.urlopen(request)
    content = response.read().decode('utf-8')
    return content


def down_load(page,content):
    with open('kfc_' + str(page) + '.json','w',encoding='utf-8')as fp:
        fp.write(content)



if __name__ == '__main__':
    start_page = int(input('请输入起始页码'))
    end_page = int(input('请输入结束页码'))

    for page in range(start_page,end_page+1):
        # 请求对象的定制
        request = create_request(page)
        # 获取网页源码
        content = get_content(request)
        # 下载
        down_load(page,content)

urllib异常处理

import urllib.request
import urllib.error

# url = 'https://blog.csdn.net/sulixu/article/details/1198189491'

url = 'http://www.doudan1111.com'

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36'
}

try:
    request = urllib.request.Request(url = url, headers = headers)

    response = urllib.request.urlopen(request)

    content = response.read().decode('utf-8')

    print(content)
except urllib.error.HTTPError:
    print('系统正在升级。。。')
except urllib.error.URLError:
    print('我都说了 系统正在升级。。。')

urllib代理

ProxyHandler函数用于网站封IP， 如果同一个IP访问过于频繁，那么该网站就会禁止来自该IP的访问，因此使用代理可以达到我们的目的。

import urllib.request

url = 'http://www.baidu.com/s?wd=ip'

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36'
}

# 请求对象的定制
request = urllib.request.Request(url=url, headers=headers)

# 模拟浏览器访问服务器
# response = urllib.request.urlopen(request)
# 代理IP
proxies = {
    'https': '132.21.222.121:9999'
}
# handler  build_opener  open
handler = urllib.request.ProxyHandler(proxies=proxies)

opener = urllib.request.build_opener(handler)

response = opener.open(request, timeout=50)

# 获取响应的信息
content = response.read().decode('utf-8')
print(content)

urllib代理池

import urllib.request

proxies_pool = [
    {'http': '118.24.219.131:16317'},
    {'https': '114.24.219.151:15817'},
]

import random

proxies = random.choice(proxies_pool)

url = 'http://www.baidu.com/s?wd=ip'

headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/92.0.4515.159 Safari/537.36'
}

request = urllib.request.Request(url=url, headers=headers)

handler = urllib.request.ProxyHandler(proxies=proxies)

opener = urllib.request.build_opener(handler)

response = opener.open(request, timeout=30)

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