requests
requests是一个python的第三方http库，它在python的内置模块基础上进行了封装，使我们用网络请求开发是变得轻松了很多，可以快速模拟浏览器的任何操作。
1.get请求
1.无参数
1 import requests 2 3 r1 = requests.get(url="http://www.sina.com") 4 5 print(r1.text)
2.有参数
import requests p1 = {'id': 'value1', 'code': 'value2'} r2 = requests.get("http://www.sina.com/get", params=p1) print r2.url # http://www.sina.com/get?id=xx&code=xx print r2.text
2.POST请求
1.基础
import requests form_data = {'name':'ddd','pass','ddd'} cookie = {'sessionid': 'fdsafaa'} r3 = requests.post(url = "http://www.sina.com", data=form_data, cookies=cookie) print(r3.text)
2.发送请求头和数据实例
import requests import json url = 'https://api.github.com/some/endpoint' d2 = {'some': 'data'} headers = {'content-type': 'application/json','use-agent':'Mozilla, linux'} r4 = requests.post(url, data=json.dumps(d2), headers=headers) print r4.text print r4.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.更多参数和示例
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) 参数示例
参数示例
BeautifulSoup4
BeautifulSoup是一个python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。 像是Xpath。
1.安装
pip38 install beautifulsoup4
需要依赖包soupsvise
2.使用方法
from bs4 import beautifulsoup4 import requests r1 = requests.get("http://www.sina.com") s1 = BeautifulSoup(r1.text, 'html.parser / lxml') # features="lxml / html.parser" # 找到id=div1的div标签 tag1 = s1.find(name='div', attrs={'id':'div1'}) # 找到第一个a标签 tag2 = s1.find(name= 'a') # 找到所有div标签 tag3 = s1.find_all(name = 'div') # 找到id=link的标签 tag4 = s1.select('#link')
3.对转换格式后的标签节点进行操作
1.name，标签名称
name
# tag = soup.find('a') # name = tag.name # 获取 # print(name) # tag.name = 'span' # 设置 # print(soup)
2.attrs，标签属性
# tag = soup.find('a',attrs={'id':'xxx'}) # attrs = tag.attrs # 获取 # print(attrs) # tag.attrs = {'ik':123} # 设置 # tag.attrs['id'] = 'iiiii' # 设置 # print(soup)
3.children，所有子标签
4.children，所有子子孙孙标签
5.celear，讲标签的所有子孙标签全部清空，保留标签名
6.decompose，递归删除所有标签
7.extract，递归的删除所有标签，并获取删除的标签
8.decode，转换为字符串，含当前标签;decode_contents不含当前标签
9.encode，转换微字节，含当前标签。encode_contents不含当前标签
10.find，获取匹配的第一个标签
11.find_all，获取匹配的所有标签
12.has_attr，检查标签是否具有该属性
13.get_text，获取标签内部文本内容
14.index，检查标签在某标签中的索引位置
15.
is_empty_element,是否是空标签(是否可以是空)或者自闭合标签，
判断是否是如下标签：'br' , 'hr', 'input', 'img', 'meta','spacer', 'link', 'frame', 'base'
16.当前的关联标签
17.查找某标签的关联标签
18.select,select_one,css选择器
19.标签的内容
20.append在当前标签内部追加一个标签
21.insert在当前标签内部指定位置插入一个标签
22.insert_after,insert_before在当前标签后或前插入
23.replace_with在当前标签替换为指定标签
24.创建标签之间的关系
25.wrap，将指定标签把当前标签包裹
26.unwrap，去掉当前标签，将保留其包裹的标签
基本流程
使用chrome，postman等工具获取request和response的请求头，返回头和请求体，返回体信息。
模拟用户浏览器的操作，携带登录和验证信息，取得服务器返回的数据，用beautifulsoup等工具进行分析提取数据，把数据持久化保存到本地数据库，利用取得的数据做自己的应用。
1.打开网站页面，不能直接去找爬取数据或登录的页面，会被认定为爬虫
r1 = requests.get("http://sina.com") 这里可能需要获取cookies或者在页面中取得隐藏数据，比如csrf token，认证码等 my_cookie = r1.cookies.get_dict() r1.close
2.post请求打开需要登录的页面
#这一步需要多测试分析，比如携带的cookies，返回的response信息
r2 = requests.post("http://sina.com/login", headers = { user_agren: Moliz, linux, ....... }, data = { user : xxx, pass: xxx, Uid:xxx, keep : on, } cookies=my_cookies ) print(r2.text)
3.格式化数据并获取需要的数据
s1 = BeautifulSoup(r2.text, 'lxml') div = s1.find(name='div', attrs={'id':'xxx','':''}) print(div.text)
真实实例
#!/usr/bin/env python # -*- coding:utf-8 -*- import requests # ############## 方式一 ############## """ # ## 1、首先登陆任何页面，获取cookie i1 = requests.get(url="http://dig.chouti.com/help/service") i1_cookies = i1.cookies.get_dict() # ## 2、用户登陆，携带上一次的cookie，后台对cookie中的 gpsd 进行授权 i2 = requests.post( url="http://dig.chouti.com/login", data={ 'phone': "8615131255089", 'password': "xxooxxoo", 'oneMonth': "" }, cookies=i1_cookies ) # ## 3、点赞（只需要携带已经被授权的gpsd即可） gpsd = i1_cookies['gpsd'] i3 = requests.post( url="http://dig.chouti.com/link/vote?linksId=8589523", cookies={'gpsd': gpsd} ) print(i3.text) """ # ############## 方式二 ############## """ import requests session = requests.Session() i1 = session.get(url="http://dig.chouti.com/help/service") i2 = session.post( url="http://dig.chouti.com/login", data={ 'phone': "8615131255089", 'password': "xxooxxoo", 'oneMonth': "" } ) i3 = session.post( url="http://dig.chouti.com/link/vote?linksId=8589523" ) print(i3.text) """ 抽屉新热榜
#!/usr/bin/env python # -*- coding:utf-8 -*- import requests from bs4 import BeautifulSoup # ############## 方式一 ############## # # # 1. 访问登陆页面，获取 authenticity_token # i1 = requests.get('https://github.com/login') # soup1 = BeautifulSoup(i1.text, features='lxml') # tag = soup1.find(name='input', attrs={'name': 'authenticity_token'}) # authenticity_token = tag.get('value') # c1 = i1.cookies.get_dict() # i1.close() # # # 1. 携带authenticity_token和用户名密码等信息，发送用户验证 # form_data = { # "authenticity_token": authenticity_token, # "utf8": "", # "commit": "Sign in", # "login": "wupeiqi@live.com", # 'password': 'xxoo' # } # # i2 = requests.post('https://github.com/session', data=form_data, cookies=c1) # c2 = i2.cookies.get_dict() # c1.update(c2) # i3 = requests.get('https://github.com/settings/repositories', cookies=c1) # # soup3 = BeautifulSoup(i3.text, features='lxml') # list_group = soup3.find(name='div', class_='listgroup') # # from bs4.element import Tag # # for child in list_group.children: # if isinstance(child, Tag): # project_tag = child.find(name='a', class_='mr-1') # size_tag = child.find(name='small') # temp = "项目:%s(%s); 项目路径:%s" % (project_tag.get('href'), size_tag.string, project_tag.string, ) # print(temp) # ############## 方式二 ############## # session = requests.Session() # # 1. 访问登陆页面，获取 authenticity_token # i1 = session.get('https://github.com/login') # soup1 = BeautifulSoup(i1.text, features='lxml') # tag = soup1.find(name='input', attrs={'name': 'authenticity_token'}) # authenticity_token = tag.get('value') # c1 = i1.cookies.get_dict() # i1.close() # # # 1. 携带authenticity_token和用户名密码等信息，发送用户验证 # form_data = { # "authenticity_token": authenticity_token, # "utf8": "", # "commit": "Sign in", # "login": "wupeiqi@live.com", # 'password': 'xxoo' # } # # i2 = session.post('https://github.com/session', data=form_data) # c2 = i2.cookies.get_dict() # c1.update(c2) # i3 = session.get('https://github.com/settings/repositories') # # soup3 = BeautifulSoup(i3.text, features='lxml') # list_group = soup3.find(name='div', class_='listgroup') # # from bs4.element import Tag # # for child in list_group.children: # if isinstance(child, Tag): # project_tag = child.find(name='a', class_='mr-1') # size_tag = child.find(name='small') # temp = "项目:%s(%s); 项目路径:%s" % (project_tag.get('href'), size_tag.string, project_tag.string, ) # print(temp) github
#!/usr/bin/env python # -*- coding:utf-8 -*- import time import requests from bs4 import BeautifulSoup session = requests.Session() i1 = 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', } ) soup1 = BeautifulSoup(i1.text, 'lxml') xsrf_tag = soup1.find(name='input', attrs={'name': '_xsrf'}) xsrf = xsrf_tag.get('value') current_time = time.time() i2 = session.get( url='https://www.zhihu.com/captcha.gif', params={'r': current_time, 'type': 'login'}, 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', }) with open('zhihu.gif', 'wb') as f: f.write(i2.content) captcha = input('请打开zhihu.gif文件，查看并输入验证码：') form_data = { "_xsrf": xsrf, 'password': 'xxooxxoo', "captcha": 'captcha', 'email': '424662508@qq.com' } i3 = session.post( url='https://www.zhihu.com/login/email', 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', } ) i4 = session.get( url='https://www.zhihu.com/settings/profile', 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', } ) soup4 = BeautifulSoup(i4.text, 'lxml') tag = soup4.find(id='rename-section') nick_name = tag.find('span',class_='name').string print(nick_name) 知乎
#!/usr/bin/env python # -*- coding:utf-8 -*- import re import json import base64 import rsa import requests def js_encrypt(text): b64der = 'MIGfMA0GCSqGSIb3DQEBAQUAA4GNADCBiQKBgQCp0wHYbg/NOPO3nzMD3dndwS0MccuMeXCHgVlGOoYyFwLdS24Im2e7YyhB0wrUsyYf0/nhzCzBK8ZC9eCWqd0aHbdgOQT6CuFQBMjbyGYvlVYU2ZP7kG9Ft6YV6oc9ambuO7nPZh+bvXH0zDKfi02prknrScAKC0XhadTHT3Al0QIDAQAB' der = base64.standard_b64decode(b64der) pk = rsa.PublicKey.load_pkcs1_openssl_der(der) v1 = rsa.encrypt(bytes(text, 'utf8'), pk) value = base64.encodebytes(v1).replace(b' ', b'') value = value.decode('utf8') return value session = requests.Session() i1 = session.get('https://passport.cnblogs.com/user/signin') rep = re.compile("'VerificationToken': '(.*)'") v = re.search(rep, i1.text) verification_token = v.group(1) form_data = { 'input1': js_encrypt('wptawy'), 'input2': js_encrypt('asdfasdf'), 'remember': False } i2 = session.post(url='https://passport.cnblogs.com/user/signin', data=json.dumps(form_data), headers={ 'Content-Type': 'application/json; charset=UTF-8', 'X-Requested-With': 'XMLHttpRequest', 'VerificationToken': verification_token} ) i3 = session.get(url='https://i.cnblogs.com/EditDiary.aspx') print(i3.text) 博客园
#!/usr/bin/env python # -*- coding:utf-8 -*- import requests # 第一步：访问登陆页,拿到X_Anti_Forge_Token，X_Anti_Forge_Code # 1、请求url:https://passport.lagou.com/login/login.html # 2、请求方法:GET # 3、请求头: # User-agent r1 = requests.get('https://passport.lagou.com/login/login.html', headers={ 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36', }, ) X_Anti_Forge_Token = re.findall("X_Anti_Forge_Token = '(.*?)'", r1.text, re.S)[0] X_Anti_Forge_Code = re.findall("X_Anti_Forge_Code = '(.*?)'", r1.text, re.S)[0] print(X_Anti_Forge_Token, X_Anti_Forge_Code) # print(r1.cookies.get_dict()) # 第二步：登陆 # 1、请求url:https://passport.lagou.com/login/login.json # 2、请求方法:POST # 3、请求头: # cookie # User-agent # Referer:https://passport.lagou.com/login/login.html # X-Anit-Forge-Code:53165984 # X-Anit-Forge-Token:3b6a2f62-80f0-428b-8efb-ef72fc100d78 # X-Requested-With:XMLHttpRequest # 4、请求体： # isValidate:true # username:15131252215 # password:ab18d270d7126ea65915c50288c22c0d # request_form_verifyCode:'' # submit:'' r2 = requests.post( 'https://passport.lagou.com/login/login.json', headers={ 'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36', 'Referer': 'https://passport.lagou.com/login/login.html', 'X-Anit-Forge-Code': X_Anti_Forge_Code, 'X-Anit-Forge-Token': X_Anti_Forge_Token, 'X-Requested-With': 'XMLHttpRequest' }, data={ "isValidate": True, 'username': '15131255089', 'password': 'ab18d270d7126ea65915c50288c22c0d', 'request_form_verifyCode': '', 'submit': '' }, cookies=r1.cookies.get_dict() ) print(r2.text) 拉勾网