urllib基本使用

urllib基本使用

​ 官方文档：https://docs.python.org/zh-cn/3/library/urllib.html

​ Python urllib 库用于操作网页 URL，并对网页的内容进行抓取处理，包含4个模块：request、error、parse、robotparser

request

​ 最基本的 http 请求模块，可以用来发送 http 请求，并接收服务端的响应数据；下面例举了一些 urllib 的 request 模块基础方法使用案例：

import urllib.request

url = 'http://www.baidu.com'
# 发送请求
response = urllib.request.urlopen(url)
# 打印 response 类型:<class 'http.client.HTTPResponse'>
print(type(response))
# 获取响应页面源码(read 读取的是二进制的数据),并以 utf-8 格式解码
content = response.read().decode('utf-8')
# 获取响应页面源码的前5个字节内容
response.read(5)
# 读取响应页面源码的一行内容
line = response.readline()
# 一行一行获取响应页面源码的内容直至结束(打印为空,暂时不知道为什么)
lines = response.readlines()
# 获取状态码
code = response.getcode()
# 获取访问的 url
url = response.geturl()
# 获取响应头
headers = response.getheaders()

​ 下载文件

# 下载文件,可以是网页、图片、视频......;第一个参数:文件 url,第二个参数:下载的文件名
urllib.request.urlretrieve(url, 'baidu.html')

构造 Request 发送请求

​ 有的网站会识别请求是否携带 UA，如果没有则认为该请求是非正常请求，而不会返回数据给你；所以有的时候需要构造 Request 携带 UA 进行访问

# 设置 UA
header = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36'
}
# 设置 Request,注意:设置参数时带上参数名(默认第二个参数是 data)
request = urllib.request.Request(url='https://www.baidu.com', headers=header)

https_content = urllib.request.urlopen(request).read().decode('utf8')

​ UA介绍：User Agent 中文名为用户代理，简称 UA，它是一个特殊字符串头，使得服务器能够识别客户使用的操作系统 及版本、CPU 类型、浏览器及版本；浏览器内核、浏览器渲染引擎、浏览器语言、浏览器插件等(F12 打开浏览器控制台，可以在一个请求的 Request Headers 中看到 UA 的相关信息)

parse

​ 有时候我们发送请求时需要携带一些参数，需要将参数转化成 unicode 编码格式后再拼接至 url，否则会报 UnicodeEncodeError 错误

​ 单个参数编码

import urllib.request
import urllib.parse

header = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36'
}

# 将参数转化成 unicode 编码格式成后拼接至 url
url = 'https://www.baidu.com/s?wd=' + urllib.parse.quote('博客园')

request = urllib.request.Request(url=url, headers=header)
response = urllib.request.urlopen(request)
content = response.read().decode('utf8')

​ 多个参数编码

import urllib.request
import urllib.parse

header = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36'
}
url = 'https://www.baidu.com/s?'

data = {
    'wd': '小明',
    'sex': '男'
}
# 将参数转化成 unicode 编码格式成后拼接至 url
url = url + urllib.parse.urlencode(data)

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

​ post 请求

import urllib.request
import urllib.parse
import json


url = 'https://fanyi.baidu.com/v2transapi?from=zh&to=en'
# 百度翻译有反爬,需要携带 Cookie,否则返回错误(如果参数都对但是请求报错考虑是否缺失请求头信息)
header = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36',
    'Cookie':'BIDUPSID=FE844A67B2FF56C5ADABC85593863D5C; PSTM=1667189167; BAIDUID=6D23EF3A381CB93BF5C068B9D4FDEA14:FG=1; APPGUIDE_10_0_2=1; REALTIME_TRANS_SWITCH=1; FANYI_WORD_SWITCH=1; HISTORY_SWITCH=1; SOUND_SPD_SWITCH=1; SOUND_PREFER_SWITCH=1; BDORZ=B490B5EBF6F3CD402E515D22BCDA1598; Hm_lvt_64ecd82404c51e03dc91cb9e8c025574=1672211305; BDSFRCVID=avtOJeC627YLYa3jGtkwhhHrzKoEzoJTH6ao5T1ROv0CoasKvifEEG0PXU8g0KFM3JSsogKK3gOTH4DF_2uxOjjg8UtVJeC6EG0Ptf8g0f5; H_BDCLCKID_SF=tbPqVCIbJK03j48kb-o5Mt-HenryqURZ5mAqofcMfnnmqRFCyp6Ny6K7QP5qL4rp3JcnaIQqabb-ShRuDx7J04rLb-RNQt543bRTbRLy5KJvEq6KqtTBhP-UyNbMWh37JgnlMKoaMp78jR093JO4y4Ldj4oxJpOJ5JbMonLafD-KMCP9jT8-en8_bU_XKPQe2CvX0n5b2R3_KROkepnKQM4pbt-qJtr75gTW_bFKWMoqOCQ2QU5-MMC9bxnnBT5ht23x3tTlBbbhh-oj2fRS358kQN3T3qLO5bRiLl6KLtjkDn3oyTbJXp0nj-Oly5jtMgOBBJ0yQ4b4OR5JjxonDh83bG7MJPKtfJPH_Ct2JDPKbn6vb-Qoq4tSeUJBWURZ5mAqotnp2ROlfRFCyPvVy6K7QP5la-od2eQnaIQqaKodhxTzKxT-QMDLb4_O-lv43bRT-hCy5KJvfq6CKU7khP-UyNbMWh37JgnlMKoaMp78jR093JO4y4Ldj4oxJpOJ5JbMonLafD8WhCI9D6tben-W5gTKbPcha5-X3buQbRcO8pcNLTDKetAuLG59afbJ25T3Bpn-Mq6BDn5GXpO1j4_eWlOvBCrBQeOfXq6cbJTtsq5jDh3B25ksD-RlW6JZL57y0hvctb3cShPmQMjrDRLbXU6BK5vPbNcZ0l8K3l02V-bIe-t2b6QhDNAHq6kHJbksL-35HJj2jJQv2KTjh6P_5lO9BtQmJJufhlRwKCO8sPbc5P7sybDhyUn4htRZQg-q3RAaQIjC8PLxLPnHKUPBMfj40x-jLNbPVn0MWhQYhpcbKPnJyUnybPnnBT3R3H8HL4nv2JcJbM5m3x6qLTKkQN3T-PKO5bRh_CcJ-J8XhC-mjjQP; BA_HECTOR=a4ah0k258hah8ha40g8502541hqqij41j; delPer=0; PSINO=7; ZFY=7mb8SwFsz7cnjNmOUQlaxa5L1Q4su3qRs06N4WXJHYE:C; BAIDUID_BFESS=6D23EF3A381CB93BF5C068B9D4FDEA14:FG=1; BDSFRCVID_BFESS=avtOJeC627YLYa3jGtkwhhHrzKoEzoJTH6ao5T1ROv0CoasKvifEEG0PXU8g0KFM3JSsogKK3gOTH4DF_2uxOjjg8UtVJeC6EG0Ptf8g0f5; H_BDCLCKID_SF_BFESS=tbPqVCIbJK03j48kb-o5Mt-HenryqURZ5mAqofcMfnnmqRFCyp6Ny6K7QP5qL4rp3JcnaIQqabb-ShRuDx7J04rLb-RNQt543bRTbRLy5KJvEq6KqtTBhP-UyNbMWh37JgnlMKoaMp78jR093JO4y4Ldj4oxJpOJ5JbMonLafD-KMCP9jT8-en8_bU_XKPQe2CvX0n5b2R3_KROkepnKQM4pbt-qJtr75gTW_bFKWMoqOCQ2QU5-MMC9bxnnBT5ht23x3tTlBbbhh-oj2fRS358kQN3T3qLO5bRiLl6KLtjkDn3oyTbJXp0nj-Oly5jtMgOBBJ0yQ4b4OR5JjxonDh83bG7MJPKtfJPH_Ct2JDPKbn6vb-Qoq4tSeUJBWURZ5mAqotnp2ROlfRFCyPvVy6K7QP5la-od2eQnaIQqaKodhxTzKxT-QMDLb4_O-lv43bRT-hCy5KJvfq6CKU7khP-UyNbMWh37JgnlMKoaMp78jR093JO4y4Ldj4oxJpOJ5JbMonLafD8WhCI9D6tben-W5gTKbPcha5-X3buQbRcO8pcNLTDKetAuLG59afbJ25T3Bpn-Mq6BDn5GXpO1j4_eWlOvBCrBQeOfXq6cbJTtsq5jDh3B25ksD-RlW6JZL57y0hvctb3cShPmQMjrDRLbXU6BK5vPbNcZ0l8K3l02V-bIe-t2b6QhDNAHq6kHJbksL-35HJj2jJQv2KTjh6P_5lO9BtQmJJufhlRwKCO8sPbc5P7sybDhyUn4htRZQg-q3RAaQIjC8PLxLPnHKUPBMfj40x-jLNbPVn0MWhQYhpcbKPnJyUnybPnnBT3R3H8HL4nv2JcJbM5m3x6qLTKkQN3T-PKO5bRh_CcJ-J8XhC-mjjQP; __bid_n=184f128997e3755a704207; FEID=v10-08ddd07c15dd88d197f4e7f8bfcaf7b5e9fb30de; __xaf_fpstarttimer__=1672304282882; __xaf_ths__={"data":{"0":1,"1":43200,"2":60},"id":"8e46496e-1a9f-4f9a-a78a-1d07b987c7c0"}; __xaf_thstime__=1672304282925; FPTOKEN=fDAYMZZw8zbLcUKBWuajW+qKbwAEUqx1CeV6NzuPMFFJp7/4sKoA4c+U51hYM1V66Ml3sIP14RBbug7OHtV/iiVK8IWdYZOqUrIhUvOvE+Ors70OxBA2HrZgQRDzfZHA+S9z1qHX2Bw14n/HybBABbuf1xhrKQ+HATw4f2Ysll8M05xMQq+smOVrnPXbQ0JSaC4GXTv5JUVnbj/VKnsoV51ZEcXTzYW3iH/djONTjjY0swy5IiaxI3dHvDViOhXKDOh1E1/vQg1vPsH9mHSML62TSw+bcc97em8PkbRmPA7mYBbPDlOMlbp1b3eL67aUDSTUm358wSSbmY9HUsXYXw5MSUeAJr/vRqzmMQVeUlMk7Qk+/YgePe0VfqhsGEj/MTPeSl6/n3WSuelrfQA1sQ==|yf3XNK7EdJvOYIq7WLxJ/XrzCOpvI8lp/P0XHJkwhgE=|10|e474f348bc2b35ee7ee8b88336293351; __xaf_fptokentimer__=1672304283063; H_PS_PSSID=36558_37647_37689_37625_36920_36802_37930_37900_26350_37959_37881; Hm_lpvt_64ecd82404c51e03dc91cb9e8c025574=1672319616; ab_sr=1.0.1_NTk0YTRhZjliYzE3MDczYWQ5ZjczNzY0ZDEwYzQxOWExN2ZjNjAyNTViN2I3ODI1M2Y3MzE3ZDNjMjY2MDNjZDQ3YzVjZTZiZDI2NjU1MWY5NmQ1M2Y3OGQwYTM3MjFlMzUzNDBlZjBmMGI0Y2E2M2QzNDY2NGRlNjI4MDM3ZWQyOGUyNTZmMDljNWIyMzUzNDQyMDc3Y2EzZjAzODYzOQ=='
}

data = {
    'from': 'zh',
    'to': 'en',
    'query': '朋友',
    'transtype': 'tanslang',
    'simple_means_flag': 3,
    'sign': 646578.867971,
    'token': '69f8f800722d4702e68dc07ddecc2054',
    'domain': 'common'
}
# 将参数转化成 unicode 编码格式(并以 utf-8 编码)
data_encode = urllib.parse.urlencode(data).encode('utf-8')
# post 请求参数需要放在 Request 中
request = urllib.request.Request(url=url, data=data_encode, headers=header)

response = urllib.request.urlopen(request)
content = response.read().decode('utf-8')
# 将字符串内容转化成 python 对象
obj_content = json.loads(content)
# 将 python 对象转化成 json 字符串,ensure_ascii=False: 忽略字符集编码
json_content = json.dumps(obj_content, ensure_ascii=False)

print(json_content)

​ 如果在 Request 中指定了 data 参数，那么 urlopen 默认发送 post 请求；当设置了 data 参数后指定 method 参数为 get，那么 data 数据并不会提交给服务器

实战

爬取豆瓣电影排行榜指定页数据（get 请求）

import urllib.request
import urllib.parse


# 获取请求头
def get_request(page_no):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36'
    }

    url = 'https://movie.douban.com/j/chart/top_list?type=5&interval_id=100:90&action=&'

    param = {
        'start': (page_no - 1) * 20,
        'limit': 20
    }
    url = url + urllib.parse.urlencode(param)
    return urllib.request.Request(url=url, headers=headers)


if __name__ == '__main__':
    page_start = int(input('请输入起始页码:'))
    page_end = int(input('请输入结束页码:'))
    # range 用法: https://blog.csdn.net/TUSTer_/article/details/122280110
    for page_no in range(page_start, page_end + 1):
        request = get_request(page_no)
        # 返回的是 json 数据
        content = urllib.request.urlopen(request).read().decode('utf-8')
        '''
        打开一个文件并返回一个文件(open 方法默认使用 gbk 编码,如果要保存汉字需要指定 utf-8 编码)
        参考: https://blog.csdn.net/a379749/article/details/123994571
        '''
        file = open('movie-douban-' + str(page_no) + '.json', 'w', encoding='utf-8')
        
        file.write(content)
        file.close()

​ 以上写数据到文件代码还有另一种写法：

with open('movie-douban-' + str(page_no) + '.json', 'w', encoding='utf-8') as file:
    file.write(content)
    file.close()

爬取肯德基餐厅地址指定页数据（post 请求）

import urllib.request
import urllib.parse


# 获取请求头
def get_request(page_no):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36'
    }

    url = 'http://www.kfc.com.cn/kfccda/ashx/GetStoreList.ashx?op=keyword'

    param = {
        'cname': '',
        'pid': '',
        'keyword': '广州',
        'pageIndex': page_no,
        'pageSize': 10
    }
    data = urllib.parse.urlencode(param).encode('utf-8')
    return urllib.request.Request(url=url, data=data, headers=headers)


if __name__ == '__main__':
    page_start = int(input('请输入起始页码:'))
    page_end = int(input('请输入结束页码:'))
    for page_no in range(page_start, page_end + 1):
        request = get_request(page_no)
        # 返回的是 json 数据
        content = urllib.request.urlopen(request).read().decode('utf-8')
        with open('address-kdj-' + str(page_no) + '.json', 'w', encoding='utf-8') as file:
            file.write(content)
            file.close()

​ 有的页面需要登录之后才可以访问，此时请求头需要携带登录的 cookie 信息才能获取到页面数据；补充 referer 请求头作用：判断当前路径是不是由指定路径进来的，一般用于图片的防盗链

Handler

​ Handler 可以定制更高级的请求头，随着业务逻辑的复杂，一般的 Request 已经满足不了我们的需求，比如：动态 cookie 和代理

​ Handler 的基本使用：通过 handler 获取百度页面源码

import urllib.request
import urllib.parse


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

header = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36'
}
request = urllib.request.Request(url=url, headers=header)
# 获取 HTTPHandler 对象
handler = urllib.request.HTTPHandler()
# 获取 opener 对象
opener = urllib.request.build_opener(handler)
# 发送请求
response = opener.open(request)

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

​ 通过代理访问页面，eg：

import urllib.request
import urllib.parse

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

header = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36'
}

proxies = {'http': '117.141.155.244:53281'}

request = urllib.request.Request(url=url, headers=header)
# 获取 ProxyHandler 对象
handler = urllib.request.ProxyHandler(proxies=proxies)

opener = urllib.request.build_opener(handler)
response = opener.open(request)
content = response.read().decode('utf-8')
print(content)

​ 代理多个 ip，eg：

proxies_pool = [
    {'http': '117.141.155.244:53281'},
    {'http': '117.141.155.244:53281'}
]
# 随机获取一个代理 ip
proxies = random.choice(proxies_pool)