pip3 install requests

pip3 install beautifulsoup4  或 pip3 install bs4

#必须先安装whell依赖  （请换成国内pip源进行安装,否则容易报错）

pip install wheel

#在cmd中，输入python进入python。
然后输入import pip;print(pip.pep425tags.get_supported())，界面上输出当前python的版本信息，如图。

#下载地址：https://pypi.python.org/pypi/lxml/3.7.3 (网站打不开，请FQ，就可以打开)

#python3.5就选择cp3m版本
lxml-3.7.3-cp35-cp35m-win32.whl

#安装方法
pip3 install lxml-3.6.4-cp35-cp35m-win_amd64.whl

response = requests.get(\'URL\')  
                response.text  # 获取文本内容
                response.content  # 获取文本内容，字节
                response.encoding  # 设置返回结果的编码
                response.aparent_encoding  # 获取网站原始的编码
                response.status_code  # 状态码
                response.cookies.get_dict()  # cookies

- 方法关系

- 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.nulige.com\',
                    params = {\'k1\':\'v1\',\'k2\':\'v2\'}
                )
                # http://www.nulige.com?k1=v1&k2=v2
            - data:    在请求体里传递的数据
            
                requests.request(
                    method=\'POST\',
                    url= \'http://www.nulige.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      基本认证(headers中加入加密的用户名和密码)
             
            　　　　 - timeout  请求和响应的超时时间
             
            　　　　 - allow_redirects  是否允许重定向
             
            　　　　 - proxies   代理 （nginx反向代理模块）
             
            　　　　 - verify   是否忽略证书
             
            　　　　 - cert     证书文件
             
            　　　　 - stream   流的方式迭代下载
             
            　　　　- session: 用于保存客户端历史访问信息

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)

with open(\'weixin.html\',\'wb\') as f:
    f.write(wx_login_page.content)

#!/usr/bin/env python
# -*- coding:utf-8 -*- 
# Author: nulige
import requests
from bs4 import BeautifulSoup
response = requests.get(
    url=\'http://www.autohome.com.cn/news/\'
)
#解决爬虫乱码问题
response.encoding = response.apparent_encoding  
# 生成Soup对象，
soup = BeautifulSoup(response.text, features=\'html.parser\')
# find查找第一个符合条件的对象
target = soup.find(id=\'auto-channel-lazyload-article\')
#find_all查找所有符合的对象，查找出来的值在列表中
li_list = target.find_all(\'li\')
#循环拿到具体每个对象
for i in li_list:
    a = i.find(\'a\')
    if a:
        print(a.attrs.get(\'href\'))   #    # .attrs查找到属性
        txt = a.find(\'h3\').text  # 是对象
        img_url = a.find(\'img\').attrs.get(\'src\')
        print(img_url)
        # 再发一个请求
        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)


备注：
　# 找到第一个a标签

#!/usr/bin/env python
# -*- coding: utf8 -*-
# __Author: "Skiler Hao"
# date: 2017/5/10 11:06
import requests
from bs4 import BeautifulSoup
# 第一次请求
first_request_response = requests.get(
    url = \'http://dig.chouti.com/\',
)
# 获取第一次登录获取的cookie内容
firstget_cookie_dict = first_request_response.cookies.get_dict()
# 登录POST请求
post_dict = {
    \'phone\': \'8618811*****\', #86+手机号码
    \'password\': \'******\',    #密码
    \'oneMonth\': 1
}
# 发送请求，携带cookie和数据
login_response = requests.post(
    url = \'http://dig.chouti.com/login\',
    data = post_dict,
    cookies= firstget_cookie_dict
)
# 点赞请求
dianzan_response = requests.post(
    url = \'http://dig.chouti.com/link/vote?linksId=11832246\',
    cookies= firstget_cookie_dict
)
print(dianzan_response.text)
# 取消点赞
cancel_dianzan_response = requests.post(
    url = \'http://dig.chouti.com/vote/cancel/vote.do\',
    cookies= firstget_cookie_dict,
    data={\'linksId\':11832246}
)
print(cancel_dianzan_response.text)
# 获取个人信息
get_person_info_resonse = requests.get(
    url = \'http://dig.chouti.com/profile\',
    cookies= firstget_cookie_dict,
)
# 按照某种encoding方式编码
get_person_info_resonse.encoding = get_person_info_resonse.apparent_encoding
# 将其内容放入BS中进行解析
person_info_site = BeautifulSoup(get_person_info_resonse.text,features=\'html.parser\')
# 找到之后可以做任何处理，获取配置中的nickname
nickname_tag = person_info_site.find(id=\'nick\')
nickname = person_info_site.find(id=\'nick\').attrs.get(\'value\')
print(\'昵称：\',nickname)
# 更新自己在抽屉上的个人信息
personal_info = {
    \'jid\': \'cdu_49017916793\',
    \'nick\': \'努力哥\',
    \'imgUrl\': \'http://img2.chouti.com/CHOUTI_90A38B32473A49B7B26A49F46B34268C_W585H359=C60x60.png\',
# http://img2.chouti.com/CHOUTI_BAE7F736FE7B48E49D1CEE459020F3B0_W390H390=48x48.jpg
    \'sex\': True,
    \'proveName\': \'北京\',
    \'cityName\': \'澳门\',
    \'sign\': \'黑hi呃呃哈发到付\'
}
update_person_info_resonse = requests.post(
    url = \'http://dig.chouti.com/profile/update\',
    cookies= firstget_cookie_dict,
    data=personal_info
)
print(update_person_info_resonse.text)
#########################Session方式登录抽屉#########################
session = requests.Session()
# 先登陆一下抽屉网
i1 = session.get(
    url=\'http://dig.chouti.com/\'
)
# 模拟抽屉登录
login_post_dict = {
    \'phone\': \'86188116*****\', #86+手机号码
    \'password\': \'******\',  #密码
    \'oneMonth\': 1
}
i2 = session.post(
    url=\'http://dig.chouti.com/login\',
    data=login_post_dict,
)

#!/usr/bin/env python
# -*- coding: utf8 -*-
# date: 2017/5/10 16:32
import requests
from bs4 import BeautifulSoup
# GitHub是基于authenticity_token，具有预防csrf_token的功能
# 首先访问页面，获取页面上的authenticity_token
i1 = requests.get(\'https://github.com/login\')
# print(i1.content)
login_page_res = BeautifulSoup(i1.content,features=\'lxml\')
authenticity_token = login_page_res.find(name=\'input\',attrs={\'name\':\'authenticity_token\'}).attrs.get(\'value\')
cookies1 = i1.cookies.get_dict()
# print(authenticity_token)
form_data = {
    \'commit\': \'Sign in\',
    \'utf8\': \'✓\',
    \'authenticity_token\': authenticity_token,
    \'login\': \'*****\',
    \'password\': \'******\',
}
# 将数据封装在post请求中进行登录，而且要加上cookie
login_res = requests.post(
    url=\'https://github.com/session\',
    data=form_data,
    cookies=cookies1
)
# print(login_res.text)
# 拿到页面中的自己的项目列表
login_page_res = BeautifulSoup(login_res.content,features=\'lxml\')
list_info = login_page_res.select("span .repo")
for i in list_info:
    print(i.text)
cookies1 = i1.cookies.get_dict()

pip3 install rsa

#!/usr/bin/env python
# -*- coding: utf8 -*-
# date: 2017/5/11 10:51
import re
import json
import base64
import rsa
import requests
from bs4 import BeautifulSoup
# 负责模仿前端js模块对账号和密码加密
def js_enrypt(text):
    # 先从博客园拿到public key
    public_key = \'MIGfMA0GCSqGSIb3DQEBAQUAA4GNADCBiQKBgQCp0wHYbg/NOPO3nzMD3dndwS0MccuMeXCHgVlGOoYyFwLdS24Im2e7YyhB0wrUsyYf0/nhzCzBK8ZC9eCWqd0aHbdgOQT6CuFQBMjbyGYvlVYU2ZP7kG9Ft6YV6oc9ambuO7nPZh+bvXH0zDKfi02prknrScAKC0XhadTHT3Al0QIDAQAB\'
    # 将拿到的一串字符，转换成64进制
    der = base64.standard_b64decode(public_key)
    # 再将其转换成数字，作为公钥加载
    pk = rsa.PublicKey.load_pkcs1_openssl_der(der)
    # 运用公钥对传进来的文字进行加密
    v1 = rsa.encrypt(bytes(text,\'utf8\'),pk)
    # 对加密后的内容进行解码
    value = base64.encodebytes(v1).replace(b\'\n\',b\'\')
    value = value.decode(\'utf8\')
    # 将其返回
    return value
session = requests.Session()
# 写个错误的用户名和密码，提交一下。就找到提交数据
post_data = {
    \'input1\': js_enrypt(\'******\'),
    \'input2\': js_enrypt(\'******\'),
    \'remember\': True
}
# 发送一次请求，获取ajax发送post时要发送的VerificationToken，需要将其放在请求头部
login_page = session.get(
    url=\'https://passport.cnblogs.com/user/signin\',
)
VerificationToken = re.compile("\'VerificationToken\': \'(.*)\'")
v = re.search(VerificationToken,login_page.text)
VerificationToken = v.group(1)
# 发送请求，注意将数据json序列化，因为Accept:application/json
login_post_res = session.post(
    url=\'https://passport.cnblogs.com/user/signin\',
    data=json.dumps(post_data),
    headers={
        \'VerificationToken\': VerificationToken,
        \'X-Requested-With\': \'XMLHttpRequest\',
        \'Content-Type\': \'application/json; charset=UTF-8\'
    }
)
# 登录账号设置页
setting_page = session.get(
    url=\'https://home.cnblogs.com/set/account/\',
)
soup = BeautifulSoup(setting_page.content,features=\'lxml\')
name = soup.select_one(\'#loginName_display_block div\').get_text().strip()
print(\'你的账号名为:\',name)

#!/usr/bin/env python
# -*- coding: utf8 -*-
import requests
from bs4 import BeautifulSoup
session = requests.Session()
# 知乎会查看你的是否有用户客户端信息，没有不会让爬的
signin_page = session.get(
    url=\'https://www.zhihu.com/#signin\',
    headers={
        \'User-Agent\': \'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.98 Safari/537.36\',
    }
)
# 拿到页面的_xrf为了防止csrf攻击，post数据的时候需要提供
signin_page_tag = BeautifulSoup(signin_page.content,features=\'lxml\')
xsrf_code = signin_page_tag.find(\'input\',attrs={\'name\':\'_xsrf\'}).attrs.get(\'value\')
# 从知乎服务器获取验证码照片，发送请求POST，发现需要传入以下三个参数
# r:1494416****
# type:login
# lang:cn
import time
current_time = time.time()
yanzhengma = session.get(
    url=\'https://www.zhihu.com/captcha.gif\',
    params={
        \'r\': current_time,
        \'type\': \'login\',
        # \'lang\': \'en\' # 使用不同的语言，cn最为复杂，不加的话，最容易识别，en为立体的英文也不好识别
    },
    headers={
        \'User-Agent\': \'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.98 Safari/537.36\',
    }
)
# 将从服务器收到的验证码写入文件，可以查看啦
with open(\'zhihu.gif\', \'wb\') as f:
    f.write(yanzhengma.content)
captcha = input("请打开照片查看验证码：")
form_data = {
    \'_xsrf\': xsrf_code,
    \'password\': \'********\',
    \'captcha\': captcha,
    # \'captcha\': \'{"img_size": [200, 44], "input_points": [[40.2, 34.2], [156.2, 28.2], [138.2, 24.2]]}\',
    # \'captcha_type\': \'cn\',  # 如果为中文的验证码比较复杂
    \'phone_num\': \'***********\',  #填手机号码登录
    # \'email\':"sddasd@123.com"  # 邮箱登录的方式
}
login_response = session.post(
    url=\'https://www.zhihu.com/login/phone_num\', #前端会根据你的数据类型选择用邮箱或者手机号码登录
    # url=\'https://www.zhihu.com/login/phone_num\'
    data=form_data,
    headers = {
        \'User-Agent\': \'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.98 Safari/537.36\',
    }
)
index_page = session.get(
    url=\'https://www.zhihu.com/\',
    headers={
        \'User-Agent\': \'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.98 Safari/537.36\',
    }
)
index_page_tag = BeautifulSoup(index_page.content,features=\'lxml\')
print(index_page_tag)