| #介绍:使用requests可以模拟浏览器的请求,比起之前用到的urllib,requests模块的api更加便捷(本质就是封装了urllib3) |
| |
| #注意:requests库发送请求将网页内容下载下来以后,并不会执行js代码,这需要我们自己分析目标站点然后发起新的request请求 |
| |
| #安装:pip3 install requests |
| |
| #各种请求方式:常用的就是requests.get()和requests.post() |
| >>> import requests |
| >>> r = requests.get('https://api.github.com/events') |
| >>> r = requests.post('http://httpbin.org/post', data = {'key':'value'}) |
| >>> r = requests.put('http://httpbin.org/put', data = {'key':'value'}) |
| >>> r = requests.delete('http://httpbin.org/delete') |
| >>> r = requests.head('http://httpbin.org/get') |
| >>> r = requests.options('http://httpbin.org/get') |
| |
| #建议在正式学习requests前,先熟悉下HTTP协议 |
| http://www.cnblogs.com/linhaifeng/p/6266327.html |
官网链接:http://docs.python-requests.org/en/master/
| import requests |
| response=requests.get('http: |
| print(response.text) |
自己拼接GET参数
| |
| import requests |
| response=requests.get('https://www.baidu.com/s?wd=python&pn=1', |
| headers={ |
| 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.75 Safari/537.36', |
| }) |
| print(response.text) |
| |
| |
| from urllib.parse import urlencode |
| wd='egon老师' |
| encode_res=urlencode({'k':wd},encoding='utf-8') |
| keyword=encode_res.split('=')[1] |
| print(keyword) |
| |
| url='https://www.baidu.com/s?wd=%s&pn=1' %keyword |
| |
| response=requests.get(url, |
| headers={ |
| 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.75 Safari/537.36', |
| }) |
| res1=response.text |
params参数的使用
| |
| from urllib.parse import urlencode |
| wd='egon老师' |
| pn=1 |
| |
| response=requests.get('https://www.baidu.com/s', |
| params={ |
| 'wd':wd, |
| 'pn':pn |
| }, |
| headers={ |
| 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/62.0.3202.75 Safari/537.36', |
| }) |
| res2=response.text |
| |
| |
| with open('a.html','w',encoding='utf-8') as f: |
| f.write(res1) |
| with open('b.html', 'w', encoding='utf-8') as f: |
| f.write(res2) |
| |
| Host |
| Referer |
| User-Agent |
| Cookie |
| |
| import requests |
| response=requests.get('https://www.zhihu.com/explore') |
| response.status_code |
| |
| |
| headers={ |
| 'User-Agent':'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/46.0.2490.76 Mobile Safari/537.36', |
| |
| } |
| respone=requests.get('https://www.zhihu.com/explore', |
| headers=headers) |
| print(respone.status_code) |
| |
| |
| |
| import requests |
| |
| Cookies={ 'user_session':'wGMHFJKgDcmRIVvcA14_Wrt_3xaUyJNsBnPbYzEL6L0bHcfc', |
| } |
| |
| response=requests.get('https://github.com/settings/emails', |
| cookies=Cookies) |
| |
| print('378533872@qq.com' in response.text) |
| #GET请求 |
| HTTP默认的请求方法就是GET |
| * 没有请求体 |
| * 数据必须在1K之内! |
| * GET请求数据会暴露在浏览器的地址栏中 |
| |
| GET请求常用的操作: |
| 1. 在浏览器的地址栏中直接给出URL,那么就一定是GET请求 |
| 2. 点击页面上的超链接也一定是GET请求 |
| 3. 提交表单时,表单默认使用GET请求,但可以设置为POST |
| |
| #POST请求 |
| (1). 数据不会出现在地址栏中 |
| (2). 数据的大小没有上限 |
| (3). 有请求体 |
| (4). 请求体中如果存在中文,会使用URL编码! |
| |
| #!!!requests.post()用法与requests.get()完全一致,特殊的是requests.post()有一个data参数,用来存放请求体数据 |
自动登录github(自己处理cookie信息)
| 一 目标站点分析 |
| 浏览器输入https://github.com/login |
| 然后输入错误的账号密码,抓包 |
| 发现登录行为是post提交到:https://github.com/session |
| 而且请求头包含cookie |
| 而且请求体包含: |
| commit:Sign in |
| utf8:✓ |
| authenticity_token:lbI8IJCwGslZS8qJPnof5e7ZkCoSoMn6jmDTsL1r/m06NLyIbw7vCrpwrFAPzHMep3Tmf/TSJVoXWrvDZaVwxQ== |
| login:egonlin |
| password:123 |
| |
| 二 流程分析 |
| 先GET:https://github.com/login拿到初始cookie与authenticity_token |
| 返回POST:https://github.com/session, 带上初始cookie,带上请求体(authenticity_token,用户名,密码等) |
| 最后拿到登录cookie |
ps:如果密码时密文形式,则可以先输错账号,输对密码,然后到浏览器中拿到加密后的密码,github的密码是明文
| |
| ''' |
| |
| import requests |
| import re |
| |
| #第一次请求 |
| r1=requests.get('https: |
| r1_cookie=r1.cookies.get_dict() |
| authenticity_token=re.findall(r'name="authenticity_token".*?value="(.*?)"',r1.text)[0] |
| |
| |
| data={ |
| 'commit':'Sign in', |
| 'utf8':'✓', |
| 'authenticity_token':authenticity_token, |
| 'login':'317828332@qq.com', |
| 'password':'alex3714' |
| } |
| r2=requests.post('https://github.com/session', |
| data=data, |
| cookies=r1_cookie |
| ) |
| |
| login_cookie=r2.cookies.get_dict() |
| |
| |
| r3=requests.get('https://github.com/settings/emails', |
| cookies=login_cookie) |
| |
| print('317828332@qq.com' in r3.text) |
requests.session()自动帮我们保存cookie信息
| import requests |
| import re |
| |
| session=requests.session() |
| |
| r1=session.get('https://github.com/login') |
| authenticity_token=re.findall(r'name="authenticity_token".*?value="(.*?)"',r1.text)[0] |
| |
| |
| data={ |
| 'commit':'Sign in', |
| 'utf8':'✓', |
| 'authenticity_token':authenticity_token, |
| 'login':'317828332@qq.com', |
| 'password':'alex3714' |
| } |
| r2=session.post('https://github.com/session', |
| data=data, |
| ) |
| |
| |
| r3=session.get('https://github.com/settings/emails') |
| |
| print('317828332@qq.com' in r3.text) |
| requests.post(url='xxxxxxxx', |
| data={'xxx':'yyy'}) |
| |
| |
| requests.post(url='', |
| data={'':1,}, |
| headers={ |
| 'content-type':'application/json' |
| }) |
| |
| requests.post(url='', |
| json={'':1,}, |
| ) |
| import requests |
| respone=requests.get('http://www.jianshu.com') |
| |
| print(respone.text) |
| print(respone.content) |
| |
| print(respone.status_code) |
| print(respone.headers) |
| print(respone.cookies) |
| print(respone.cookies.get_dict()) |
| print(respone.cookies.items()) |
| |
| print(respone.url) |
| print(respone.history) |
| |
| print(respone.encoding) |
| |
| |
| from contextlib import closing |
| with closing(requests.get('xxx',stream=True)) as response: |
| for line in response.iter_content(): |
| pass |
| |
| import requests |
| response=requests.get('http://www.autohome.com/news') |
| |
| print(response.text) |
| import requests |
| |
| response=requests.get('https://timgsa.baidu.com/timg?image&quality=80&size=b9999_10000&sec=1509868306530&di=712e4ef3ab258b36e9f4b48e85a81c9d&imgtype=0&src=http%3A%2F%2Fc.hiphotos.baidu.com%2Fimage%2Fpic%2Fitem%2F11385343fbf2b211e1fb58a1c08065380dd78e0c.jpg') |
| |
| with open('a.jpg','wb') as f: |
| f.write(response.content) |
获取二进制流
| |
| |
| import requests |
| |
| response=requests.get('https://gss3.baidu.com/6LZ0ej3k1Qd3ote6lo7D0j9wehsv/tieba-smallvideo-transcode/1767502_56ec685f9c7ec542eeaf6eac93a65dc7_6fe25cd1347c_3.mp4', |
| stream=True) |
| |
| with open('b.mp4','wb') as f: |
| for line in response.iter_content(): |
| f.write(line) |
| |
| import requests |
| response=requests.get('http://httpbin.org/get') |
| |
| import json |
| res1=json.loads(response.text) |
| |
| res2=response.json() |
| |
| print(res1 == res2) |
先看官网的解释
| By default Requests will perform location redirection for all verbs except HEAD. |
| |
| We can use the history property of the Response object to track redirection. |
| |
| The Response.history list contains the Response objects that were created in order to complete the request. The list is sorted from the oldest to the most recent response. |
| |
| For example, GitHub redirects all HTTP requests to HTTPS: |
| |
| >>> r = requests.get('http://github.com') |
| |
| >>> r.url |
| 'https://github.com/' |
| |
| >>> r.status_code |
| 200 |
| |
| >>> r.history |
| [<Response [301]>] |
| If you're using GET, OPTIONS, POST, PUT, PATCH or DELETE, you can disable redirection handling with the allow_redirects parameter: |
| |
| >>> r = requests.get('http://github.com', allow_redirects=False) |
| |
| >>> r.status_code |
| 301 |
| |
| >>> r.history |
| [] |
| If you're using HEAD, you can enable redirection as well: |
| |
| >>> r = requests.head('http://github.com', allow_redirects=True) |
| |
| >>> r.url |
| 'https://github.com/' |
| |
| >>> r.history |
| [<Response [301]>] |
利用github登录后跳转到主页面的例子来验证它
| import requests |
| import re |
| |
| |
| r1=requests.get('https://github.com/login') |
| r1_cookie=r1.cookies.get_dict() |
| authenticity_token=re.findall(r'name="authenticity_token".*?value="(.*?)"',r1.text)[0] |
| |
| |
| data={ |
| 'commit':'Sign in', |
| 'utf8':'✓', |
| 'authenticity_token':authenticity_token, |
| 'login':'317828332@qq.com', |
| 'password':'alex3714' |
| } |
| |
| |
| r2=requests.post('https://github.com/session', |
| data=data, |
| cookies=r1_cookie |
| ) |
| |
| print(r2.status_code) |
| print(r2.url) |
| print(r2.history) |
| print(r2.history[0].text) |
| |
| |
| r2=requests.post('https://github.com/session', |
| data=data, |
| cookies=r1_cookie, |
| allow_redirects=False |
| ) |
| |
| print(r2.status_code) |
| print(r2.url) |
| print(r2.history) |
| |
| import requests |
| respone=requests.get('https://www.12306.cn') |
| |
| |
| import requests |
| respone=requests.get('https://www.12306.cn',verify=False) |
| print(respone.status_code) |
| |
| |
| import requests |
| from requests.packages import urllib3 |
| urllib3.disable_warnings() |
| respone=requests.get('https://www.12306.cn',verify=False) |
| print(respone.status_code) |
| |
| |
| |
| |
| |
| import requests |
| respone=requests.get('https://www.12306.cn', |
| cert=('/path/server.crt', |
| '/path/key')) |
| print(respone.status_code) |
| |
| |
| |
| import requests |
| proxies={ |
| 'http':'http://egon:123@localhost:9743', |
| 'http':'http://localhost:9743', |
| 'https':'https://localhost:9743', |
| } |
| respone=requests.get('https://www.12306.cn', |
| proxies=proxies) |
| |
| print(respone.status_code) |
| |
| |
| import requests |
| proxies = { |
| 'http': 'socks5://user:pass@host:port', |
| 'https': 'socks5://user:pass@host:port' |
| } |
| respone=requests.get('https://www.12306.cn', |
| proxies=proxies) |
| |
| print(respone.status_code) |
| #超时设置 |
| #两种超时:float or tuple |
| #timeout=0.1 |
| #timeout=(0.1,0.2) |
| |
| import requests |
| respone=requests.get('https://www.baidu.com', |
| timeout=0.0001) |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| |
| import requests |
| from requests.auth import HTTPBasicAuth |
| r=requests.get('xxx',auth=HTTPBasicAuth('user','password')) |
| print(r.status_code) |
| |
| |
| import requests |
| r=requests.get('xxx',auth=('user','password')) |
| print(r.status_code) |
| |
| import requests |
| from requests.exceptions import * |
| |
| try: |
| r=requests.get('http://www.baidu.com',timeout=0.00001) |
| except ReadTimeout: |
| print('===:') |
| |
| |
| |
| |
| |
| except RequestException: |
| print('Error') |
| import requests |
| files={'file':open('a.jpg','rb')} |
| respone=requests.post('http://httpbin.org/post',files=files) |
| print(respone.status_code) |