爬虫之Requests库

官方文档：http://cn.python-requests.org/zh_CN/latest/

一、引子

import requests

resp = requests.get("https://www.baidu.com/")
print(type(resp))  # <class 'requests.models.Response'>
print(resp.status_code)  #
# print(resp.text)
print(type(resp.text))   # <class 'str'>
# print(resp.text)
print(resp.cookies)

各种请求方式：

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")

二、请求

GET请求

基本写法：

import requests
resp = requests.get("http://httpbin.org/get")
print(resp.text)

带参数get请求：

# 方式1
resp = requests.get("http://httpbin.org/get?name=pd&age=18")
print(resp.text)
# 方式2
params = {
    "name": "pd",
    "age": 18
}
resp = requests.get("http://httpbin.org/get", params=params)
print(resp.text)

解析json：

resp = requests.get("http://httpbin.org/get")
print(resp.json())        # 相当于json.loads(resp.text)
print(type(resp.text))    # <class 'str'>
print(type(resp.json()))  # <class 'dict'>

获取二进制数据：

resp = requests.get("https://github.com/favicon.ico")
print(type(resp.text))     # <class 'str'>
print(type(resp.content))  # <class 'bytes'>
print(resp.text)
print(resp.content)        # 获取非文本响应内容

with open("favicon.ico", "wb") as f:
    f.write(resp.content)

添加请求头：

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36"
}
resp = requests.get("https://www.zhihu.com/explore", headers=headers)
print(resp.text)

POST请求

基本操作：

data = {"name": "pd", "age": 18}
resp = requests.post("http://httpbin.org/post", data=data)
print(resp.text)

添加请求头：

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36"
}
data = {"name": "pd", "age": 18}
resp = requests.post("http://httpbin.org/post", data=data, headers=headers)
print(resp.text)

三、响应

响应属性：

resp = requests.get("https://www.jianshu.com")
print(type(resp.status_code), resp.status_code) # <class 'int'> 200
print(type(resp.headers), resp.headers)
print(type(resp.cookies), resp.cookies)     # <class 'requests.cookies.RequestsCookieJar'> <RequestsCookieJar[<Cookie locale=zh-CN for www.jianshu.com/>]>
print(type(resp.url), resp.url)             # <class 'str'> https://www.jianshu.com/
print(type(resp.history), resp.history)     # <class 'list'> []

状态码判断：

resp = requests.get("https://www.jianshu.com")
exit() if not resp.status_code == requests.codes.forbidden else print("403 Forbidden")

response = requests.get("http://www.baidu.com")
exit() if not response.status_code == 200 else print("Request Successfully")

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',),

# 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'),

状态码信息

四、高级操作

文件上传

files = {"file": open("favicon.ico", "rb")}
resp = requests.post("http://httpbin.org/post", files=files)
print(resp.text)

获取cookie

resp = requests.get("https://www.baidu.com")
print(resp.cookies)           # <RequestsCookieJar[<Cookie BDORZ=27315 for .baidu.com/>]>
for key, value in resp.cookies.items():
    print(key + "=" + value)  # BDORZ=27315

会话维持

用来做模拟登录。

requests.get("http://httpbin.org/cookies/set/num/123456")  # 设置cookie
resp = requests.get("http://httpbin.org/cookies")
print(resp.text)  # {"cookies": {}}  cookies为空是因为发起两次请求，而两此请求是完全独立的过程

声明一个session对象发起两次请求：

s = requests.Session()
s.get("http://httpbin.org/cookies/set/num/123456")
resp = s.get("http://httpbin.org/cookies")
print(resp.text)  # {"cookies": {"num": "123456"}}

证书验证

如果要爬取上述这种网站的话：

import requests
from requests.packages import urllib3
urllib3.disable_warnings()
resp = requests.get("https://www.xxx.com", verify=False)
print(resp.status_code)

代理设置

proxies = {
  "http": "http://127.0.0.1:9743",
  "https": "https://127.0.0.1:9743",
}
resp = requests.get("https://www.xxx.com", proxies=proxies)
print(resp.status_code)

如果不是http、https代理，而是socks代理：

pip3 install 'requests[socks]'

proxies = {
    "http": "socks5://127.0.0.1:9742",
    "https": "socks5://127.0.0.1:9742"
}
response = requests.get("https://www.xxx.com", proxies=proxies)
print(response.status_code)

超时设置

为防止服务器不能及时响应，大部分发至外部服务器的请求都应该带着 timeout 参数。在默认情况下，除非显式指定了 timeout 值，requests 是不会自动进行超时处理的。如果没有 timeout，你的代码可能会挂起若干分钟甚至更长时间。

import requests
from requests import exceptions
try:
    resp = requests.get("http://httpbin.org/get", timeout=0.5)
    print(resp.status_code)
except exceptions.ReadTimeout:
    print("ReadTimeout")
except exceptions.ConnectTimeout:
    print("ConnectTimeout")

认证设置

有些网站需要登录才能看到里面的内容：

import requests
from requests.auth import HTTPBasicAuth
resp = requests.get("http://111.11.11.11:9001", auth=HTTPBasicAuth("user", ""))
print(resp.status_code)

异常处理

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

import requests
from requests.exceptions import ReadTimeout, ConnectionError, RequestException
try:
    resp = requests.get("http://httpbin.org/get", timeout=0.5)
    print(resp.status_code)
except ReadTimeout:
    print("Timeout")
except ConnectionError:
    print("Connection error")
except RequestException:
    print("Error")