爬虫3：requests库

一个简单易用的http库

简单例子

import requests

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

print(type(response))

print(response.status_code)

print(type(response.text)) //字符串类型

print(response.text)

print(response.cookies)

一. requests的几种请求方式

import requests

requests.post(' http://httpbin.org/post')

requests.put(' http://httpbin.org/put')

requests.delete(' http://httpbin.org/delete')

requests.head(' http://httpbin.org/get')

requests.options(' http://httpbin.org/get')

1. 基本GET请求

import requests

response = requests.get(' http://httpbin.org/get')

print(response.text)

2. 带参数的GET请求

import requests

response = requests.get(" http://httpbin.org/get?name=germey&age=22")

print(response.text)

使用params参数简化操作

import requests

data = {

'name': 'germey',

'age': 22

}

response = requests.get(" http://httpbin.org/get", params=data)

print(response.text)

3. 解析json

import requests

import json

response = requests.get(" http://httpbin.org/get")

print(type(response.text))

print(response.json())

print(json.loads(response.text))

print(type(response.json())

4. 获取2进制数据

import requests

response = requests.get(" https://github.com/favicon.ico")

print(type(response.text), type(response.content))

print(response.text) //和下面的做比较

print(response.content) //获取2进制内容

保存2进制文件

import requests

response = requests.get(" https://github.com/favicon.ico")

with open('favicon.ico', 'wb') as f:

f.write(response.content)

f.close()

5. 添加headers

import requests

response = requests.get(" https://www.zhihu.com/explore")

print(response.text)

上面代码不加header内容会报错500，修改如下即可

import requests

headers = {

'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36'

}

response = requests.get(" https://www.zhihu.com/explore", headers=headers)

print(response.text)

二. 基本POST请求

import requests

data = {'name': 'germey', 'age': '22'}

response = requests.post(" http://httpbin.org/post", data=data)

print(response.text)

加一个header

import requests

data = {'name': 'germey', 'age': '22'}

headers = {

'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_11_4) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/52.0.2743.116 Safari/537.36'

}

response = requests.post(" http://httpbin.org/post", data=data, headers=headers)

print(response.json())

三. 响应

1. response属性

import requests

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

print(type(response.status_code), response.status_code)

print(type(response.headers), response.headers)

print(type(response.cookies), response.cookies)

print(type(response.url), response.url)

print(type(response.history), response.history)

2. 状态码判断

1）使用状态码相对应文本

import requests

response = requests.get(' http://www.jianshu.com/hello.html')

exit() if not response.status_code == requests.codes. not_found else print('404 Not Found')

2）使用状态码数字

import requests

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

exit() if not response.status_code == 200 else print('Request Successfully')

3）状态码对应文本

100: ('continue',),

101: ('switching_protocols',),

102: ('processing',),

103: ('checkpoint',),

122: ('uri_too_long', 'request_uri_too_long'),

200: ('ok', 'okay', 'all_ok', 'all_okay', 'all_good', '\\o/', '✓'),

201: ('created',),

202: ('accepted',),

203: ('non_authoritative_info', 'non_authoritative_information'),

204: ('no_content',),

205: ('reset_content', 'reset'),

206: ('partial_content', 'partial'),

207: ('multi_status', 'multiple_status', 'multi_stati', 'multiple_stati'),

208: ('already_reported',),

226: ('im_used',),

# Redirection.

300: ('multiple_choices',),

301: ('moved_permanently', 'moved', '\\o-'),

302: ('found',),

303: ('see_other', 'other'),

304: ('not_modified',),

305: ('use_proxy',),

306: ('switch_proxy',),

307: ('temporary_redirect', 'temporary_moved', 'temporary'),

308: ('permanent_redirect',

'resume_incomplete', 'resume',), # These 2 to be removed in 3.0

# Client Error.

400: ('bad_request', 'bad'),

401: ('unauthorized',),

402: ('payment_required', 'payment'),

403: ('forbidden',),

404: ('not_found', '-o-'),

405: ('method_not_allowed', 'not_allowed'),

406: ('not_acceptable',),

407: ('proxy_authentication_required', 'proxy_auth', 'proxy_authentication'),

408: ('request_timeout', 'timeout'),

409: ('conflict',),

410: ('gone',),

411: ('length_required',),

412: ('precondition_failed', 'precondition'),

413: ('request_entity_too_large',),

414: ('request_uri_too_large',),

415: ('unsupported_media_type', 'unsupported_media', 'media_type'),

416: ('requested_range_not_satisfiable', 'requested_range', 'range_not_satisfiable'),

417: ('expectation_failed',),

418: ('im_a_teapot', 'teapot', 'i_am_a_teapot'),

421: ('misdirected_request',),

422: ('unprocessable_entity', 'unprocessable'),

423: ('locked',),

424: ('failed_dependency', 'dependency'),

425: ('unordered_collection', 'unordered'),

426: ('upgrade_required', 'upgrade'),

428: ('precondition_required', 'precondition'),

429: ('too_many_requests', 'too_many'),

431: ('header_fields_too_large', 'fields_too_large'),

444: ('no_response', 'none'),

449: ('retry_with', 'retry'),

450: ('blocked_by_windows_parental_controls', 'parental_controls'),

451: ('unavailable_for_legal_reasons', 'legal_reasons'),

499: ('client_closed_request',),

# Server Error.

500: ('internal_server_error', 'server_error', '/o\\', '✗'),

501: ('not_implemented',),

502: ('bad_gateway',),

503: ('service_unavailable', 'unavailable'),

504: ('gateway_timeout',),

505: ('http_version_not_supported', 'http_version'),

506: ('variant_also_negotiates',),

507: ('insufficient_storage',),

509: ('bandwidth_limit_exceeded', 'bandwidth'),

510: ('not_extended',),

511: ('network_authentication_required', 'network_auth', 'network_authentication'),

4. 高级操作

1. 文件上传，使用files参数

import requests

files = {'file': open('favicon.ico', 'rb')} //指定文件名为file

response = requests.post(" http://httpbin.org/post", files=files)

print(response.text)

2. 获取cookie

import requests

response = requests.get(" https://www.baidu.com")

print(response.cookies) //列表形式

for key, value in response.cookies.items():

print(key + '=' + value)

3. 会话维持

模拟登陆

例子1，在测试网站httpbin.org中实验

import requests

requests.get(' http://httpbin.org/cookies/set/number/123456789')

response = requests.get(' http://httpbin.org/cookies')

print(response.text)

上面代码返回空，没获得cookie信息，原因是使用了2次requests.get方法，相当于开启了2个浏览器

例子2，在同一个浏览器中获得cookie，使用requests.Session()

import requests

s = requests.Session()

s.get(' http://httpbin.org/cookies/set/number/123456789') //设置cookie

response = s.get(' http://httpbin.org/cookies') //获得cookie

print(response.text)

返回结果如下

{"cookies":{"number":"123456789"}}

4. 证书验证,解决https问题

import requests

response = requests.get(' https://www.12306.cn')

print(response.status_code)

使用requests.get()方法来访问URL时，如果发现https证书不合法会报SSLError错误，并中断

解决方法为加一个verify=False参数，并禁止警报

import requests

from requests.packages import urllib3

urllib3.disable_warnings()

response = requests.get(' https://www.12306.cn', verify=False)

print(response.status_code)

自己上传证书

import requests

response = requests.get(' https://www.12306.cn', cert=('/path/server.crt', '/path/key'))

print(response.status_code)

5. 代理设置

1）无用户名和密码的代理

import requests

proxies = {

"http": "http://127.0.0.1:9743",

"https": "https://127.0.0.1:9743",

}

response = requests.get(" https://www.taobao.com", proxies=proxies)

print(response.status_code)

2）有用户名和密码的代理

import requests

proxies = {

"http": " http://user:[email protected]:9743/",

}

response = requests.get(" https://www.taobao.com", proxies=proxies)

print(response.status_code)

3）不是http,https代理，而是socks代理的情况

pip3 install 'requests[socks]'

import requests

proxies = {

'http': 'socks5://127.0.0.1:9742',

'https': 'socks5://127.0.0.1:9742'

}

response = requests.get(" https://www.taobao.com", proxies=proxies)

print(response.status_code)

6. 超时设置

import requests

from requests.exceptions import ReadTimeout

try:

response = requests.get(" http://httpbin.org/get", timeout = 0.5)

print(response.status_code)

except ReadTimeout:

print('Timeout')

7. 认证设置

有些网站需要输入用户名和密码才能看到网页内容

方法1

import requests

from requests.auth import HTTPBasicAuth

r = requests.get('http://120.27.34.24:9001', auth=HTTPBasicAuth('user', '123')) //传入用户名和密码

print(r.status_code)

方法2

import requests

r = requests.get('http://120.27.34.24:9001', auth=('user', '123'))

print(r.status_code)

8. 异常处理

import requests

from requests.exceptions import ReadTimeout, ConnectionError, RequestException

try:

response = requests.get(" http://httpbin.org/get", timeout = 0.5)

print(response.status_code)

except ReadTimeout: //超时捕获这个异常

print('Timeout')

except ConnectionError: //网络有问题时捕获这个异常

print('Connection error')

except RequestException:

print('Error')

参考

http://www.python-requests.org/en/master/api/#exceptions

猜你喜欢