Requests初步
阶段大纲:
一. 爬虫
1. 基本操作
- 登录任意网站(伪造浏览器的任何行为)
2. 性能相关
- 并发方案:
- 异步IO: gevent/Twisted/asyncio/aiohttp
- 自定义异步IO模块
- IO多路复用:select
3. Scrapy框架
介绍:异步IO:Twisted
- 基于Scrapy源码自定义爬虫框架
- 使用Scrapy
二. Tornado框架(异步非阻塞)
1. Tornado的基本使用
- 小示例
- 自定义组件
2. Tornado源码剖析
3. 自定义异步非阻塞框架 select实现
1. 爬虫基本操作
a. 爬虫
- 定向
- 非定向
b.
需求一:
下载页面:
http://www.autohome.com.cn/news/
筛选:
正则表达式
========== 开源模块 ==========
1. requests
pip3 install requests
response = requests.get('http://www.autohome.com.cn/news/')
response.text
总结:
response = requests.get('URL')
response.text
response.content
response.encoding
response.aparent_encoding
response.status_code
response.cookies.get_dict()
requests.get('http://www.autohome.com.cn/news/',cookie={'xx':'xxx'})
2. beautisoup模块
pip3 install beautifulsoup4
from bs4 import BeautiSoup
soup = BeautiSoup(response.text,features='html.parser')
target = soup.find(id='auto-channel-lazyload-article')
print(target)
总结:
soup = beautifulsoup('<html>...</html>',features='html.parser')
v1 = soup.find('div')
v1 = soup.find(id='i1')
v1 = soup.find('div',id='i1')
v2 = soup.find_all('div')
v2 = soup.find_all(id='i1')
v2 = soup.find_all('div',id='i1')
obj = v1
obj = v2[0]
obj.text
obj.attrs
需求二:
通过程序自动登录github
post_dict = {
"phone": '111111111',
'password': 'xxx',
'oneMonth': 1
}
response = requests.post(
url="http://dig.chouti.com/login",
data = post_dict
)
print(response.text)
cookie_dict = response.cookies.get_dict()
c. 模块详细使用
requests
- 方法关系
requests.get(.....)
requests.post(.....)
requests.put(.....)
requests.delete(.....)
...
requests.request('POST'...)
- 参数
request.request
- method: 提交方式
- url: 提交地址
- params: 在URL中传递的参数,GET
requests.request(
method='GET',
url= 'http://www.oldboyedu.com',
params = {'k1':'v1','k2':'v2'}
)
# http://www.oldboyedu.com?k1=v1&k2=v2
- data: 在请求体里传递的数据
requests.request(
method='POST',
url= 'http://www.oldboyedu.com',
params = {'k1':'v1','k2':'v2'},
data = {'use':'alex','pwd': '123','x':[11,2,3]}
)
请求头:
content-type: application/url-form-encod.....
请求体:
use=alex&pwd=123
- json 在请求体里传递的数据
requests.request(
method='POST',
url= 'http://www.oldboyedu.com',
params = {'k1':'v1','k2':'v2'},
json = {'use':'alex','pwd': '123'}
)
请求头:
content-type: application/json
请求体:
"{'use':'alex','pwd': '123'}"
PS: 字典中嵌套字典时
- headers 请求头
requests.request(
method='POST',
url= 'http://www.oldboyedu.com',
params = {'k1':'v1','k2':'v2'},
json = {'use':'alex','pwd': '123'},
headers={
'Referer': 'http://dig.chouti.com/',
'User-Agent': "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36"
}
)
- cookies Cookies
- files 上传文件
- auth 基本认知(headers中加入加密的用户名和密码)
- timeout 请求和响应的超市时间
- allow_redirects 是否允许重定向
- proxies 代理
- verify 是否忽略证书
- cert 证书文件
- stream 村长下大片
- session: 用于保存客户端历史访问信息
#!/usr/bin/env python #-*- coding:utf-8 -*- # Author: JianBao Yu import requests response = requests.get('http://www.autohome.com.cn/news/') # response.text # response.encoding = 'gbk' response.encoding = response.apparent_encoding from bs4 import BeautifulSoup soup = BeautifulSoup(response.text,features='html.parser') target = soup.find(id='auto-channel-lazyload-article') li_list = target.find_all('li') for i in li_list: a = i.find('a') if a: print(a.attrs.get('href')) txt = a.find('img') h3 = a.find('h3') src=txt.attrs.get('src') #字符串 print(h3) file_name = src.split('__')[-1] print(file_name) srcc = requests.get(src) if srcc: srcc.encoding = srcc.apparent_encoding with open(file_name,'wb') as f: f.write(srcc.content) # print(target) # http://www3.autoimg.cn/newsdfs/g21/M03/6D/10/120x90_0_autohomecar__wKgFVVkN_16ASy3oAABwKu_xtvs373.jpg
1.爬取汽车之家部分图片
#!/usr/bin/env python #-*- coding:utf-8 -*- # Author: JianBao Yu import requests from bs4 import BeautifulSoup response = requests.get( url='http://www.autohome.com.cn/news/' ) response.encoding = response.apparent_encoding soup = BeautifulSoup(response.text,features='html.parser') target = soup.find(id='auto-channel-lazyload-article') li_list = target.find_all('li') for i in li_list: a = i.find('a') if a: print(a.attrs.get('href')) txt = a.find('h3').text # 什么类型? print(txt) img_url = a.find('img').attrs.get('src') print(img_url) img_response = requests.get(url=img_url) import uuid file_name = str(uuid.uuid4()) + '.jpg' with open(file_name,'wb') as f: f.write(img_response.content) import requests post_dict = { "phone": '8615131255089', 'password': 'woshiniba', 'oneMonth': 1 } response = requests.post( url="http://dig.chouti.com/login", data=post_dict ) print(response.text) cookie_dict = response.cookies.get_dict() print(cookie_dict) response = requests.get( url='http://dig.chouti.com/profile', cookies=cookie_dict ) print(response.text) import requests #带着cookies去点赞 ret = requests.post( url='http://dig.chouti.com/link/vote?linksId=11825081', cookies={ 'gpsd': 'c9c202cc9fe82779c2bf87b34809019b' } ) print(ret.text) import requests #使用session对象,不需要再带cookies去登陆和和获取信息 session = requests.Session() ### 1、首先登陆任何页面,获取cookie i1 = session.get(url="http://dig.chouti.com/help/service") ### 2、用户登陆,携带上一次的cookie,后台对cookie中的 gpsd 进行授权 i2 = session.post( url="http://dig.chouti.com/login", data={ 'phone': "8615131255089", 'password': "woshiniba", 'oneMonth': "" } ) i3 = session.post( url="http://dig.chouti.com/link/vote?linksId=11837086", ) print(i3.text) import requests #使用代理,通过代理发送请求,不需要通过本机 post_dict = { "phone": '8615131255089', 'password': 'woshiniba', 'oneMonth': 1 } response = requests.post( url="http://dig.chouti.com/login", data=post_dict, proxys={ 'http': "http://4.19.128.5:8099" } ) import requests #文件上传 # requests.post( # url='xxx', # files={ # 'f1': open('s1.py','rb'), # 'f2': ('ssssss1.py',open('s1.py','rb')) #可以是元组的形式,ssssss1上传到服务器的文件名 # } # ) #授权 def param_auth(): #请求头的验证,通过请求头的用户名和密码进行加密,放在请求头发送。 from requests.auth import HTTPBasicAuth, HTTPDigestAuth ret = requests.get('https://api.github.com/user', auth=HTTPBasicAuth('wupeiqi', 'sdfasdfasdf')) #路由器后台管理,遵循请求头验证。 # ret = requests.get('https://api.github.com/user',headers={'Authorization':_basic_auth_str(self.username, self.password)}) print(ret.text) # ret = requests.get('http://192.168.1.1', # auth=HTTPBasicAuth('admin', 'admin')) # ret.encoding = 'gbk' # print(ret.text) # ret = requests.get('http://httpbin.org/digest-auth/auth/user/pass', auth=HTTPDigestAuth('user', 'pass')) # print(ret) # import requests # requests.post( # url='xxx', # files={ # 'f1': open('s1.py','rb'), # 'f2': ('ssssss1.py',open('s1.py','rb')) # } # ) requests.get( url='https:xxxx', # verify=False #是否需要进行证书验证,false就不用证书验证,忽略证书的存在。 # cert='fuck.pem' #是个证书,服务器端给的证书格式 # cert=('fuck.crt','xxx.key') #支持两个证书验证,可以合并处理等 )
2.部分使用案例。
Python标准库中提供了:urllib、urllib2、httplib等模块以供Http请求,但是,它的 API 太渣了。它是为另一个时代、另一个互联网所创建的。它需要巨量的工作,甚至包括各种方法覆盖,来完成最简单的任务。
Requests 是使用 Apache2 Licensed 许可证的 基于Python开发的HTTP 库,其在Python内置模块的基础上进行了高度的封装,从而使得Pythoner进行网络请求时,变得美好了许多,使用Requests可以轻而易举的完成浏览器可有的任何操作。
1、GET请求
# 1、无参数实例 import requests ret = requests.get('https://github.com/timeline.json') print ret.url print ret.text # 2、有参数实例 import requests payload = {'key1': 'value1', 'key2': 'value2'} ret = requests.get("http://httpbin.org/get", params=payload) print ret.url print ret.text
2、POST请求
# 1、基本POST实例 import requests payload = {'key1': 'value1', 'key2': 'value2'} ret = requests.post("http://httpbin.org/post", data=payload) print ret.text # 2、发送请求头和数据实例 import requests import json url = 'https://api.github.com/some/endpoint' payload = {'some': 'data'} headers = {'content-type': 'application/json'} ret = requests.post(url, data=json.dumps(payload), headers=headers) print ret.text print ret.cookies
3、其他请求
requests.get(url, params=None, **kwargs) requests.post(url, data=None, json=None, **kwargs) requests.put(url, data=None, **kwargs) requests.head(url, **kwargs) requests.delete(url, **kwargs) requests.patch(url, data=None, **kwargs) requests.options(url, **kwargs) # 以上方法均是在此方法的基础上构建 requests.request(method, url, **kwargs)
4、更多参数
def request(method, url, **kwargs): """Constructs and sends a :class:`Request <Request>`. :param method: method for the new :class:`Request` object. :param url: URL for the new :class:`Request` object. :param params: (optional) Dictionary or bytes to be sent in the query string for the :class:`Request`. :param data: (optional) Dictionary, bytes, or file-like object to send in the body of the :class:`Request`. :param json: (optional) json data to send in the body of the :class:`Request`. :param headers: (optional) Dictionary of HTTP Headers to send with the :class:`Request`. :param cookies: (optional) Dict or CookieJar object to send with the :class:`Request`. :param files: (optional) Dictionary of ``'name': file-like-objects`` (or ``{'name': file-tuple}``) for multipart encoding upload. ``file-tuple`` can be a 2-tuple ``('filename', fileobj)``, 3-tuple ``('filename', fileobj, 'content_type')`` or a 4-tuple ``('filename', fileobj, 'content_type', custom_headers)``, where ``'content-type'`` is a string defining the content type of the given file and ``custom_headers`` a dict-like object containing additional headers to add for the file. :param auth: (optional) Auth tuple to enable Basic/Digest/Custom HTTP Auth. :param timeout: (optional) How long to wait for the server to send data before giving up, as a float, or a :ref:`(connect timeout, read timeout) <timeouts>` tuple. :type timeout: float or tuple :param allow_redirects: (optional) Boolean. Set to True if POST/PUT/DELETE redirect following is allowed. :type allow_redirects: bool :param proxies: (optional) Dictionary mapping protocol to the URL of the proxy. :param verify: (optional) whether the SSL cert will be verified. A CA_BUNDLE path can also be provided. Defaults to ``True``. :param stream: (optional) if ``False``, the response content will be immediately downloaded. :param cert: (optional) if String, path to ssl client cert file (.pem). If Tuple, ('cert', 'key') pair. :return: :class:`Response <Response>` object :rtype: requests.Response Usage:: >>> import requests >>> req = requests.request('GET', 'http://httpbin.org/get') <Response [200]> """
def param_method_url(): # requests.request(method='get', url='http://127.0.0.1:8000/test/') # requests.request(method='post', url='http://127.0.0.1:8000/test/') pass def param_param(): # - 可以是字典 # - 可以是字符串 # - 可以是字节(ascii编码以内) # requests.request(method='get', # url='http://127.0.0.1:8000/test/', # params={'k1': 'v1', 'k2': '水电费'}) # requests.request(method='get', # url='http://127.0.0.1:8000/test/', # params="k1=v1&k2=水电费&k3=v3&k3=vv3") # requests.request(method='get', # url='http://127.0.0.1:8000/test/', # params=bytes("k1=v1&k2=k2&k3=v3&k3=vv3", encoding='utf8')) # 错误 # requests.request(method='get', # url='http://127.0.0.1:8000/test/', # params=bytes("k1=v1&k2=水电费&k3=v3&k3=vv3", encoding='utf8')) pass def param_data(): # 可以是字典 # 可以是字符串 # 可以是字节 # 可以是文件对象 # requests.request(method='POST', # url='http://127.0.0.1:8000/test/', # data={'k1': 'v1', 'k2': '水电费'}) # requests.request(method='POST', # url='http://127.0.0.1:8000/test/', # data="k1=v1; k2=v2; k3=v3; k3=v4" # ) # requests.request(method='POST', # url='http://127.0.0.1:8000/test/', # data="k1=v1;k2=v2;k3=v3;k3=v4", # headers={'Content-Type': 'application/x-www-form-urlencoded'} # ) # requests.request(method='POST', # url='http://127.0.0.1:8000/test/', # data=open('data_file.py', mode='r', encoding='utf-8'), # 文件内容是:k1=v1;k2=v2;k3=v3;k3=v4 # headers={'Content-Type': 'application/x-www-form-urlencoded'} # ) pass def param_json(): # 将json中对应的数据进行序列化成一个字符串,json.dumps(...) # 然后发送到服务器端的body中,并且Content-Type是 {'Content-Type': 'application/json'} requests.request(method='POST', url='http://127.0.0.1:8000/test/', json={'k1': 'v1', 'k2': '水电费'}) def param_headers(): # 发送请求头到服务器端 requests.request(method='POST', url='http://127.0.0.1:8000/test/', json={'k1': 'v1', 'k2': '水电费'}, headers={'Content-Type': 'application/x-www-form-urlencoded'} ) def param_cookies(): # 发送Cookie到服务器端 requests.request(method='POST', url='http://127.0.0.1:8000/test/', data={'k1': 'v1', 'k2': 'v2'}, cookies={'cook1': 'value1'}, ) # 也可以使用CookieJar(字典形式就是在此基础上封装) from http.cookiejar import CookieJar from http.cookiejar import Cookie obj = CookieJar() obj.set_cookie(Cookie(version=0, name='c1', value='v1', port=None, domain='', path='/', secure=False, expires=None, discard=True, comment=None, comment_url=None, rest={'HttpOnly': None}, rfc2109=False, port_specified=False, domain_specified=False, domain_initial_dot=False, path_specified=False) ) requests.request(method='POST', url='http://127.0.0.1:8000/test/', data={'k1': 'v1', 'k2': 'v2'}, cookies=obj) def param_files(): # 发送文件 # file_dict = { # 'f1': open('readme', 'rb') # } # requests.request(method='POST', # url='http://127.0.0.1:8000/test/', # files=file_dict) # 发送文件,定制文件名 # file_dict = { # 'f1': ('test.txt', open('readme', 'rb')) # } # requests.request(method='POST', # url='http://127.0.0.1:8000/test/', # files=file_dict) # 发送文件,定制文件名 # file_dict = { # 'f1': ('test.txt', "hahsfaksfa9kasdjflaksdjf") # } # requests.request(method='POST', # url='http://127.0.0.1:8000/test/', # files=file_dict) # 发送文件,定制文件名 # file_dict = { # 'f1': ('test.txt', "hahsfaksfa9kasdjflaksdjf", 'application/text', {'k1': '0'}) # } # requests.request(method='POST', # url='http://127.0.0.1:8000/test/', # files=file_dict) pass def param_auth(): from requests.auth import HTTPBasicAuth, HTTPDigestAuth ret = requests.get('https://api.github.com/user', auth=HTTPBasicAuth('wupeiqi', 'sdfasdfasdf')) print(ret.text) # ret = requests.get('http://192.168.1.1', # auth=HTTPBasicAuth('admin', 'admin')) # ret.encoding = 'gbk' # print(ret.text) # ret = requests.get('http://httpbin.org/digest-auth/auth/user/pass', auth=HTTPDigestAuth('user', 'pass')) # print(ret) # def param_timeout(): # ret = requests.get('http://google.com/', timeout=1) # print(ret) # ret = requests.get('http://google.com/', timeout=(5, 1)) # print(ret) pass def param_allow_redirects(): ret = requests.get('http://127.0.0.1:8000/test/', allow_redirects=False) print(ret.text) def param_proxies(): # proxies = { # "http": "61.172.249.96:80", # "https": "http://61.185.219.126:3128", # } # proxies = {'http://10.20.1.128': 'http://10.10.1.10:5323'} # ret = requests.get("http://www.proxy360.cn/Proxy", proxies=proxies) # print(ret.headers) # from requests.auth import HTTPProxyAuth # # proxyDict = { # 'http': '77.75.105.165', # 'https': '77.75.105.165' # } # auth = HTTPProxyAuth('username', 'mypassword') # # r = requests.get("http://www.google.com", proxies=proxyDict, auth=auth) # print(r.text) pass def param_stream(): ret = requests.get('http://127.0.0.1:8000/test/', stream=True) print(ret.content) ret.close() # from contextlib import closing # with closing(requests.get('http://httpbin.org/get', stream=True)) as r: # # 在此处理响应。 # for i in r.iter_content(): # print(i) def requests_session(): import requests session = requests.Session() ### 1、首先登陆任何页面,获取cookie i1 = session.get(url="http://dig.chouti.com/help/service") ### 2、用户登陆,携带上一次的cookie,后台对cookie中的 gpsd 进行授权 i2 = session.post( url="http://dig.chouti.com/login", data={ 'phone': "8615131255089", 'password': "xxxxxx", 'oneMonth': "" } ) i3 = session.post( url="http://dig.chouti.com/link/vote?linksId=8589623", ) print(i3.text)
官方文档:http://cn.python-requests.org/zh_CN/latest/user/quickstart.html#id4
BeautifulSoup是一个模块,该模块用于接收一个HTML或XML字符串,然后将其进行格式化,之后遍可以使用他提供的方法进行快速查找指定元素,从而使得在HTML或XML中查找指定元素变得简单。
from bs4 import BeautifulSoup html_doc = """ <html><head><title>The Dormouse's story</title></head> <body> asdf <div class="title"> <b>The Dormouse's story总共</b> <h1>f</h1> </div> <div class="story">Once upon a time there were three little sisters; and their names were <a class="sister0" id="link1">Els<span>f</span>ie</a>, <a href="http://example.com/lacie" class="sister" id="link2">Lacie</a> and <a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>; and they lived at the bottom of a well.</div> ad<br/>sf <p class="story">...</p> </body> </html> """ soup = BeautifulSoup(html_doc, features="lxml") # 找到第一个a标签 tag1 = soup.find(name='a') # 找到所有的a标签 tag2 = soup.find_all(name='a') # 找到id=link2的标签 tag3 = soup.select('#link2')
安装: