爬虫学习--requests库

import json
import requests
from requests.exceptions import RequestException
import faker
from multiprocessing import Pool

fake = faker.Factory.create()
headers = {
    'Connection': 'keep-alive',
    'User-Agent': fake.user_agent()
}

# 获取网页代码通用框架
def get_html(url):
    try:
        resopnse = requests.get(url=url, headers=headers)
        if resopnse.status_code == 200:
            resopnse.encoding = resopnse.apparent_encoding
            html = resopnse.text
            return html
    except RequestException:
        return None


if __name__ == '__main__':

    url = 'http://www.httpbin.org/'
    content = get_html(url)

    # requests库学习
    # 控制访问的参数**kwargs(13个)

    # 重点
    # params 字典或字节序列，作为参数增加到url中
    payload = {'key1': 'value1', 'key2': 'value2'}
    r_get = requests.get(url='http://www.httpbin.org/get', params=payload)

    # data 字典，字节序列或文件对象，作为request的内容
    kv = {'key1': 'value1', 'key2': 'value2'}
    r_post = requests.post(url='http://www.httpbin.org/post', data=kv)
    # body = '主题内容'
    r_post = requests.post(url='http://www.httpbin.org/post', data=body)


    # json json格式的数据，作为request的内容
    kv = {'key1': 'value1', 'key2': 'value2'}
    r_post = requests.post(url='http://www.httpbin.org/post', json=kv)

    # headers 字典http定制头
    fake = faker.Factory.create()
    headers = {
        'Connection': 'keep-alive',
        'User-Agent': fake.user_agent()
    }
    r_get = requests.get(url='http://www.httpbin.org/post', headers=headers)


    # cookies 字典或CookieJar，Request中的cooies
    # auth 元组，支持http认证功能
    # files 字典类型，传输文件
    # timeout 设定超时时间，秒为单位

    # proxies 字典类型，设定访问代理服务器，可以增加登录认证
    pxs = {'http': 'http://user:pass@10.10.10.1:1234',
           'https': 'https://10.10.10.1:1234'
    }
    r = requests.get('http://www.baidu.com', proxies=pxs)

    # 高级
    # allow_redirects True/False,默认为True，重定向开关
    # stream Ture/False,默认为True,获取内容立即下载开关
    # verify True/False，默认为True,认证ssl则证书开关
    # cert 本地ssl证书路径

    # get 请求
    payload = {'key1': 'value1', 'key2': 'value2'}
    r_get = requests.get(url+'get', headers=headers, params=payload)
    print(r_get.url)
    print(r_get.status_code)
    print(r_get.headers)
    print(r_get.text)
    print(r_get.json())
    print(r_get.content)
    print(r_get.cookies)
    print(r_get.apparent_encoding)



    # # post 请求
    payload = {'key1': 'value1', 'key2': 'value2'}
    r_post = requests.post(url=url+'post', headers=headers, params=json.dumps(payload))
    print(r_post.url)
    comp = requests.post(url=url+'post', headers=headers, params=payload)
    print(comp.url)
    print(r_post.status_code)
    print(r_post.headers)
    print(r_post.text)
    print(r_post.json())
    print(r_post.content)
    print(r_post.apparent_encoding)

    # 搜索引擎关键词提交接口
    # 谷歌 https://www.google.com/search?q=keyword
    # 百度 http://www.baidu.com/s?wd=keyword

    url1 = 'https://www.ip138.com/iplookup.asp?ip=113.247.70.95&action=2'
    html = get_html(url1)
    print(html)