python爬虫之requests模块

import requests

#先获取页面

r1 = requests.get('http://dig.chouti.com/')
r1_COOKIEs = r1.COOKIEs.get_dict()

#登录
post_dict = {
    "phone":"8615131255089",
    "password":"woshiniba",
    "oneMonth":"1"
}

r2 = requests.post(
    url="http://dig.chouti.com/login",
    data = post_dict,
    COOKIEs=r1_COOKIEs
)

r2_COOKIEs = r2.COOKIEs.get_dict()

# 访问其他页面
r3 = requests.post(
    url="http://dig.chouti.com/link/vote?linksId=13921091",
    COOKIEs={'gpsd':r1_COOKIEs['gpsd']}
)
print(r3.text)

import requests
from bs4 import BeautifulSoup

r1 = requests.get('https://github.com/login')
s1 = BeautifulSoup(r1.text,'html.parser')

# 获取csrf_token
token = s1.find(name='input',attrs={'name':"authenticity_token"}).get('value')
r1_COOKIE_dict = r1.COOKIEs.get_dict()

# 将用户名 密码 token 发送到服务端 post
r2 = requests.post(
    'https://github.com/session',
    data={
    'commit':'Sign in',
    'utf8':'✓',
    'authenticity_token':token,
    'login':'317828332@qq.com',
    'password':'alex3714'
    },
    COOKIEs=r1_COOKIE_dict
)

#  获取登录后COOKIE
r2_COOKIE_dict = r2.COOKIEs.get_dict()

#合并登录前的COOKIE和登录后的COOKIE
COOKIE_dict = {}
COOKIE_dict.update(r1_COOKIE_dict)
COOKIE_dict.update(r2_COOKIE_dict)




r3 = requests.get(
    url='https://github.com/settings/emails',
    COOKIEs=COOKIE_dict
)

print(r3.text)

import requests

requests.post(
    url='xxx',
    filter={
        'name1': open('a.txt','rb'),   #名称对应的文件对象
        'name2': ('bbb.txt',open('b.txt','rb'))     #表示上传到服务端的名称为 bbb.txt
    }
)

import requests

requests.post(
    url='xxx',
    filter={
        'name1': open('a.txt','rb'),   #名称对应的文件对象
        'name2': ('bbb.txt',open('b.txt','rb'))     #表示上传到服务端的名称为 bbb.txt
    }
)

#如果服务器文件过大,循环下载

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)

    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)