s10day112 内容回顾： 第一部分：爬虫相关 1. 谈谈你对http协议的理解？ 规范： 1. Http请求收发数据的格式 GET /index/ http1.1/r/nhost:xxx.com/r/n/r/n POST /index/ http1.1/r/nhost:xxx.com/r/n/r/nuser=xxx 2. 短连接（无状态） 一次请求一次响应之后，就断开连接 3. 基于TCP协议之上 sk = socket() sk.send('GET /index/ http1.1/r/nhost:xxx.com/r/n/r/n') 常见请求头有哪些？ host content-type user-agent cookies referer，上一次请求地址 常见的请求方法有哪些？ GET POST DELETE PUT PATCH OPTIONS 2. requests 用于伪造浏览器发送请求 参数： - url - headers - data - cookies 响应： - content - text - encoding='gbk' - headers - cookies.get_dict() 3. bs 用于解析HTML格式的字符串 方法和属性： - find - find_all - attrs - get - text 4. 套路 - 汽车之家 - 抽屉新闻：携带user-agent - 登录抽屉：第一访问保留cookie，登录时需要再次携带； - 自动登录github：获取csrf_token，到底携带那一个cookie 补充：自动登录github 第二部分：路飞相关 1. 公司的组织架构？ 开发： - 村长 - 前端姑娘 - 涛 - 云（产品+开发） UI：1人 测试：1人 运维：1人 运营：2人 销售：3人 班主任：1人 全职助教：2人 人事/财务：老男孩共享 2. 项目架构 - 管理后台(1) - 权限 - xadmin - 导师后台(1) - 权限 - xadmin - 主站(1+1+0.5+1) - restful api - vue.js 现在开发：题库系统 3. 涉及技术点： - django - django rest framework - vue.js - 跨域cors - redis - 支付宝支付 - 视频播放 - CC视频 - 保利 - 微信消息推送 - 已认证的服务号 - 发送模板消息 - content-type 今日内容： - 拉勾网 - 抖音 - requests - bs4 - 初识scrapy框架 内容详细： 1.拉勾网 - Token和Code存在页面上，自定义请求头上 - 重定向： - 响应头的Location中获取要重定向的地址 - 自己去处理 - 请求发送时需要携带上次请求的code和token 原则： - 完全模拟浏览器的行为 2. 爬抖音视频 3. requests模块 参数： url params headers cookies data 示例： request.post( data={ user:'alex', pwd:'sb' } ) user=alex&pwd=sb chrome: formdata json 示例： request.post( json={ user:'alex', pwd:'sb' } ) '{"user":"alex","pwd":"sb"}' chrome: request payload allow_redirecs stream files requests.post( url='xxx', files={ 'f1': open('readme', 'rb') } ) auth from requests.auth import HTTPBasicAuth, HTTPDigestAuth ret = requests.get('https://api.github.com/user', auth=HTTPBasicAuth('admin', 'admin')) print(ret.text) timeout ret = requests.get('http://google.com/', timeout=1) ret = requests.get('http://google.com/', timeout=(5, 1)) 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("https://www.proxy360.cn/Proxy", proxies=proxies) print(ret.headers) from requests.auth import HTTPProxyAuth auth = HTTPProxyAuth('username', 'mypassword') r = requests.get("http://www.google.com", proxies=proxyDict, auth=auth) 证书相关： cert verify session：自动管理cookie和headers（不建议使用） 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) 4. bs4 参考示例：https://www.cnblogs.com/wupeiqi/articles/6283017.html 预习： 1. 安装scrapy https://www.cnblogs.com/wupeiqi/articles/6229292.html a. 下载twisted http://www.lfd.uci.edu/~gohlke/pythonlibs/#twisted b. 安装wheel pip3 install wheel c. 安装twisted pip3 install Twisted‑18.7.0‑cp36‑cp36m‑win_amd64.whl d. 安装pywin32 pip3 install pywin32 e. 安装scrapy pip3 install scrapy
import requests from bs4 import BeautifulSoup r1 = requests.get( url='https://github.com/login' ) s1 = BeautifulSoup(r1.text,'html.parser') token = s1.find(name='input',attrs={'name':'authenticity_token'}).get('value') r1_cookie_dict = r1.cookies.get_dict() r2 = requests.post( url='https://github.com/session', data={ 'commit':'Sign in', 'utf8':'✓', 'authenticity_token':token, 'login':'wupeiqi@live.com', 'password':'sdfasdfasdfasdf' }, cookies=r1_cookie_dict ) r2_cookie_dict = r2.cookies.get_dict() r3 = requests.get( url='https://github.com/settings/emails', cookies=r2_cookie_dict ) print(r3.text)
import re import requests all_cookie_dict = {} # ##################################### 第一步：访问登录页面 ##################################### r1 = requests.get( url='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/67.0.3396.99 Safari/537.36' } ) token = re.findall("X_Anti_Forge_Token = '(.*)';",r1.text)[0] code = re.findall("X_Anti_Forge_Code = '(.*)';",r1.text)[0] r1_cookie_dict = r1.cookies.get_dict() all_cookie_dict.update(r1_cookie_dict) # ##################################### 第二步：去登陆 ##################################### r2 = requests.post( url='https://passport.lagou.com/login/login.json', data={ 'isValidate':'true', 'username':'15131255089', 'password':'647541545465', 'request_form_verifyCode':'', 'submit':'' }, headers={ 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36', 'X-Requested-With':'XMLHttpRequest', 'Content-Type':'application/x-www-form-urlencoded; charset=UTF-8', 'Host':'passport.lagou.com', 'Origin':'https://passport.lagou.com', 'Referer':'https://passport.lagou.com/login/login.html', 'X-Anit-Forge-Code':code, 'X-Anit-Forge-Token':token }, cookies=all_cookie_dict ) r2_response_json = r2.json() r2_cookie_dict = r2.cookies.get_dict() all_cookie_dict.update(r2_cookie_dict) # ##################################### 第三步：grant ##################################### r3 = requests.get( url='https://passport.lagou.com/grantServiceTicket/grant.html', headers={ 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36', 'Referer':'https://passport.lagou.com/login/login.html', 'Host':'passport.lagou.com', }, cookies=all_cookie_dict, allow_redirects=False ) r3_cookie_dict = r3.cookies.get_dict() all_cookie_dict.update(r3_cookie_dict) # ##################################### 第四步：action ##################################### r4 = requests.get( url=r3.headers['Location'], headers={ 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36', 'Referer':'https://passport.lagou.com/login/login.html', 'Host':'www.lagou.com', 'Upgrade-Insecure-Requests':'1', }, cookies=all_cookie_dict, allow_redirects=False ) r4_cookie_dict = r4.cookies.get_dict() all_cookie_dict.update(r4_cookie_dict) # ##################################### 第五步：获取认证信息 ##################################### r5 = requests.get( url=r4.headers['Location'], headers={ 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36', 'Referer':'https://passport.lagou.com/login/login.html', 'Host':'www.lagou.com', 'Upgrade-Insecure-Requests':'1', }, cookies=all_cookie_dict, allow_redirects=False ) r5_cookie_dict = r5.cookies.get_dict() all_cookie_dict.update(r5_cookie_dict) print(r5.headers['Location']) # ##################################### 第六步：我的邀请 ##################################### r = requests.get( url='https://www.lagou.com/mycenter/invitation.html', headers={ 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36', 'Host':'www.lagou.com', 'Upgrade-Insecure-Requests':'1', 'Pragma':'no-cache', }, cookies=all_cookie_dict ) print('wupeiqi' in r.text)
import re import requests all_cookie_dict = {} # ##################################### 第一步：访问登录页面 ##################################### r1 = requests.get( url='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/67.0.3396.99 Safari/537.36' } ) token = re.findall("X_Anti_Forge_Token = '(.*)';",r1.text)[0] code = re.findall("X_Anti_Forge_Code = '(.*)';",r1.text)[0] r1_cookie_dict = r1.cookies.get_dict() all_cookie_dict.update(r1_cookie_dict) # ##################################### 第二步：去登陆 ##################################### r2 = requests.post( url='https://passport.lagou.com/login/login.json', data={ 'isValidate':'true', 'username':'15131255089', 'password':'4565465', 'request_form_verifyCode':'', 'submit':'' }, headers={ 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36', 'X-Requested-With':'XMLHttpRequest', 'Content-Type':'application/x-www-form-urlencoded; charset=UTF-8', 'Host':'passport.lagou.com', 'Origin':'https://passport.lagou.com', 'Referer':'https://passport.lagou.com/login/login.html', 'X-Anit-Forge-Code':code, 'X-Anit-Forge-Token':token }, cookies=all_cookie_dict ) r2_response_json = r2.json() r2_cookie_dict = r2.cookies.get_dict() all_cookie_dict.update(r2_cookie_dict) # ##################################### 第三步：grant ##################################### r3 = requests.get( url='https://passport.lagou.com/grantServiceTicket/grant.html', headers={ 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36', 'Referer':'https://passport.lagou.com/login/login.html', 'Host':'passport.lagou.com', }, cookies=all_cookie_dict, allow_redirects=False ) r3_cookie_dict = r3.cookies.get_dict() all_cookie_dict.update(r3_cookie_dict) # ##################################### 第四步：action ##################################### r4 = requests.get( url=r3.headers['Location'], headers={ 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36', 'Referer':'https://passport.lagou.com/login/login.html', 'Host':'www.lagou.com', 'Upgrade-Insecure-Requests':'1', }, cookies=all_cookie_dict, allow_redirects=False ) r4_cookie_dict = r4.cookies.get_dict() all_cookie_dict.update(r4_cookie_dict) # ##################################### 第五步：获取认证信息 ##################################### r5 = requests.get( url=r4.headers['Location'], headers={ 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36', 'Referer':'https://passport.lagou.com/login/login.html', 'Host':'www.lagou.com', 'Upgrade-Insecure-Requests':'1', }, cookies=all_cookie_dict, allow_redirects=False ) r5_cookie_dict = r5.cookies.get_dict() all_cookie_dict.update(r5_cookie_dict) print(r5.headers['Location']) # ##################################### 第六步 ##################################### r6 = requests.get( url=r5.headers['Location'], headers={ 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36', 'Referer':'https://passport.lagou.com/login/login.html', 'Host':'www.lagou.com', 'Upgrade-Insecure-Requests':'1', }, cookies=all_cookie_dict, allow_redirects=False ) r6_cookie_dict = r6.cookies.get_dict() all_cookie_dict.update(r6_cookie_dict) print(r6.headers['Location']) # ##################################### 第七步 ##################################### r7 = requests.get( url=r6.headers['Location'], headers={ 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36', 'Referer':'https://passport.lagou.com/login/login.html', 'Host':'www.lagou.com', 'Upgrade-Insecure-Requests':'1', }, cookies=all_cookie_dict, allow_redirects=False ) r7_cookie_dict = r7.cookies.get_dict() all_cookie_dict.update(r7_cookie_dict) # ##################################### 第八步：查看个人信息 ##################################### r8 = requests.get( url='https://gate.lagou.com/v1/neirong/account/users/0/', headers={ 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36', 'Host':'gate.lagou.com', 'Pragma':'no-cache', 'Referer':'https://account.lagou.com/v2/account/userinfo.html', 'X-L-REQ-HEADER':'{deviceType:1}' }, cookies=all_cookie_dict ) r8_response_json = r8.json() # print(r8_response_json) all_cookie_dict.update(r8.cookies.get_dict()) # ##################################### 第九步：查看个人信息 ##################################### r9 = requests.put( url='https://gate.lagou.com/v1/neirong/account/users/0/', headers={ 'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36', 'Host':'gate.lagou.com', 'Origin':'https://account.lagou.com', 'Referer':'https://account.lagou.com/v2/account/userinfo.html', 'X-L-REQ-HEADER':'{deviceType:1}', 'X-Anit-Forge-Code':r8_response_json.get('submitCode'), 'X-Anit-Forge-Token':r8_response_json.get('submitToken'), 'Content-Type':'application/json;charset=UTF-8', }, json={"userName":"wupeiqi999","sex":"MALE","portrait":"images/myresume/default_headpic.png","positionName":"...","introduce":"...."}, cookies=all_cookie_dict ) print(r9.text)
爬抖音
<!DOCTYPE html> <html lang="en"> <head> <meta charset="UTF-8"> <title>Title</title> </head> <body> <script> !function (t) { if (t.__M = t.__M || {}, !t.__M.require) { var e, n, r = document.getElementsByTagName("head")[0], i = {}, o = {}, a = {}, u = {}, c = {}, s = {}, l = function (t, n) { if (!(t in u)) { u[t] = !0; var i = document.createElement("script"); if (n) { var o = setTimeout(n, e.timeout); i.onerror = function () { clearTimeout(o), n() } ; var a = function () { clearTimeout(o) }; "onload" in i ? i.onload = a : i.onreadystatechange = function () { ("loaded" === this.readyState || "complete" === this.readyState) && a() } } return i.type = "text/javascript", i.src = t, r.appendChild(i), i } }, f = function (t, e, n) { var r = i[t] || (i[t] = []); r.push(e); var o, a = c[t] || c[t + ".js"] || {}, u = a.pkg; o = u ? s[u].url || s[u].uri : a.url || a.uri || t, l(o, n && function () { n(t) } ) }; n = function (t, e) { "function" != typeof e && (e = arguments[2]), t = t.replace(/\.js$/i, ""), o[t] = e; var n = i[t]; if (n) { for (var r = 0, a = n.length; a > r; r++) n[r](); delete i[t] } } , e = function (t) { if (t && t.splice) return e.async.apply(this, arguments); t = e.alias(t); var n = a[t]; if (n) return n.exports; var r = o[t]; if (!r) throw "[ModJS] Cannot find module `" + t + "`"; n = a[t] = { exports: {} }; var i = "function" == typeof r ? r.apply(n, [e, n.exports, n]) : r; return i && (n.exports = i), n.exports && !n.exports["default"] && Object.defineProperty && Object.isExtensible(n.exports) && Object.defineProperty(n.exports, "default", { value: n.exports }), n.exports } , e.async = function (n, r, i) { function a(t) { for (var n, r = 0, h = t.length; h > r; r++) { var p = e.alias(t[r]); p in o ? (n = c[p] || c[p + ".js"], n && "deps" in n && a(n.deps)) : p in s || (s[p] = !0, l++, f(p, u, i), n = c[p] || c[p + ".js"], n && "deps" in n && a(n.deps)) } } function u() { if (0 === l--) { for (var i = [], o = 0, a = n.length; a > o; o++) i[o] = e(n[o]); r && r.apply(t, i) } } "string" == typeof n && (n = [n]); var s = {} , l = 0; a(n), u() } , e.resourceMap = function (t) { var e, n; n = t.res; for (e in n) n.hasOwnProperty(e) && (c[e] = n[e]); n = t.pkg; for (e in n) n.hasOwnProperty(e) && (s[e] = n[e]) } , e.loadJs = function (t) { l(t) } , e.loadCss = function (t) { if (t.content) { var e = document.createElement("style"); e.type = "text/css", e.styleSheet ? e.styleSheet.cssText = t.content : e.innerHTML = t.content, r.appendChild(e) } else if (t.url) { var n = document.createElement("link"); n.href = t.url, n.rel = "stylesheet", n.type = "text/css", r.appendChild(n) } } , e.alias = function (t) { return t.replace(/\.js$/i, "") } , e.timeout = 5e3, t.__M.define = n, t.__M.require = e } }(this) __M.define("douyin_falcon:node_modules/byted-acrawler/dist/runtime", function (l, e) { Function(function (l) { return 'e(e,a,r){(b[e]||(b[e]=t("x,y","x "+e+" y")(r,a)}a(e,a,r){(k[r]||(k[r]=t("x,y","new x[y]("+Array(r+1).join(",x[y]")(1)+")")(e,a)}r(e,a,r){n,t,s={},b=s.d=r?r.d+1:0;for(s["$"+b]=s,t=0;t<b;t)s[n="$"+t]=r[n];for(t=0,b=s=a;t<b;t)s[t]=a[t];c(e,0,s)}c(t,b,k){u(e){v[x]=e}f{g=,ting(bg)}l{try{y=c(t,b,k)}catch(e){h=e,y=l}}for(h,y,d,g,v=[],x=0;;)switch(g=){case 1:u(!)4:f5:u((e){a=0,r=e;{c=a<r;c&&u(e[a]),c}}(6:y=,u((y8:if(g=,lg,g=,y===c)b+=g;else if(y!==l)y9:c10:u(s(11:y=,u(+y)12:for(y=f,d=[],g=0;g<y;g)d[g]=y.charCodeAt(g)^g+y;u(String.fromCharCode.apply(null,d13:y=,h=delete [y]14:59:u((g=)?(y=x,v.slice(x-=g,y:[])61:u([])62:g=,k[0]=65599*k[0]+k[1].charCodeAt(g)>>>065:h=,y=,[y]=h66:u(e(t[b],,67:y=,d=,u((g=).x===c?r(g.y,y,k):g.apply(d,y68:u(e((g=t[b])<"<"?(b--,f):g+g,,70:u(!1)71:n72:+f73:u(parseInt(f,3675:if(){bcase 74:g=<<16>>16g76:u(k[])77:y=,u([y])78:g=,u(a(v,x-=g+1,g79:g=,u(k["$"+g])81:h=,[f]=h82:u([f])83:h=,k[]=h84:!085:void 086:u(v[x-1])88:h=,y=,h,y89:u({e{r(e.y,arguments,k)}e.y=f,e.x=c,e})90:null91:h93:h=0:;default:u((g<<16>>16)-16)}}n=this,t=n.Function,s=Object.keys||(e){a={},r=0;for(c in e)a[r]=c;a=r,a},b={},k={};r'.replace(/[-]/g, function (e) { return l[15 & e.charCodeAt(0)] }) }("v[x++]=v[--x]t.charCodeAt(b++)-32function return ))++.substrvar .length(),b+=;break;case ;break}".split("")))()('gr$Daten Иb/s!l y͒yĹg,(lfi~ah`{mv,-n|jqewVxp{rvmmx,&effkx[!cs"l".Pq%widthl"@q&heightl"vr*getContextx$"2d[!cs#l#,*;?|u.|uc{uq$fontl#vr(fillTextx$$龘ฑภ경2<[#c}l#2q*shadowBlurl#1q-shadowOffsetXl#$$limeq+shadowColorl#vr#arcx88802[%c}l#vr&strokex[ c}l"v,)}eOmyoZB]mx[ cs!0s$l$Pb<k7l l!r&lengthb%^l$1+s$jl s#i$1ek1s$gr#tack4)zgr#tac$! +0o![#cj?o ]!l$b%s"o ]!l"l$b*b^0d#>>>s!0s%yA0s"l"l!r&lengthb<k+l"^l"1+s"jl s&l&z0l!$ +["cs\'(0l#i\'1ps9wxb&s() &{s)/s(gr&Stringr,fromCharCodes)0s*yWl ._b&s o!])l l Jb<k$.aj;l .Tb<k$.gj/l .^b<k&i"-4j!+& s+yPo!]+s!l!l Hd>&l!l Bd>&+l!l <d>&+l!l 6d>&+l!l &+ s,y=o!o!]/q"13o!l q"10o!],l 2d>& s.{s-yMo!o!]0q"13o!]*Ld<l 4d#>>>b|s!o!l q"10o!],l!& s/yIo!o!].q"13o!],o!]*Jd<l 6d#>>>b|&o!]+l &+ s0l-l!&l-l!i\'1z141z4b/@d<l"b|&+l-l(l!b^&+l-l&zl\'g,)gk}ejo{cm,)|yn~Lij~em["cl$b%@d<l&zl\'l $ +["cl$b%b|&+l-l%8d<@b|l!b^&+ q$sign ', [Object.defineProperty(e, "__esModule", {value: !0})]) }); _bytedAcrawler = __M.require("douyin_falcon:node_modules/byted-acrawler/dist/runtime"); signature = _bytedAcrawler.sign('58841646784') console.log(signature); </script> </body> </html>
navigator = { userAgent:"Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36" } !function (t) { if (t.__M = t.__M || {}, !t.__M.require) { var e, n, r = "<head> <meta charset=\"utf-8\"><title>快来加入抖音短视频，让你发现最有趣的我！</title><meta name=\"viewport\" content=\"width=device-width,initial-scale=1,user-scalable=0,minimum-scale=1,maximum-scale=1,minimal-ui,viewport-fit=cover\"><meta name=\"format-detection\" content=\"telephone=no\"><meta name=\"baidu-site-verification\" content=\"szjdG38sKy\"><meta name=\"keywords\" content=\"抖音、抖音音乐、抖音短视频、抖音官网、amemv\"><meta name=\"description\" content=\"抖音短视频-记录美好生活的视频平台\"><meta name=\"apple-mobile-web-app-capable\" content=\"yes\"><meta name=\"apple-mobile-web-app-status-bar-style\" content=\"default\"><link rel=\"apple-touch-icon-precomposed\" href=\"//s3.bytecdn.cn/ies/resource/falcon/douyin_falcon/static/image/logo/logo_launcher_v2_40f12f4.png\"><link rel=\"shortcut icon\" href=\"//s3.bytecdn.cn/ies/resource/falcon/douyin_falcon/static/image/logo/favicon_v2_7145ff0.ico\" type=\"image/x-icon\"><meta http-equiv=\"X-UA-Compatible\" content=\"IE=Edge;chrome=1\"><meta name=\"screen-orientation\" content=\"portrait\"><meta name=\"x5-orientation\" content=\"portrait\"><script async=\"\" src=\"//www.google-analytics.com/analytics.js\"></script><script type=\"text/javascript\">!function(){function e(e){return this.config=e,this}e.prototype={reset:function(){var e=Math.min(document.documentElement.clientWidth,750)/750*100;document.documentElement.style.fontSize=e+\"px\";var t=parseFloat(window.getComputedStyle(document.documentElement).fontSize),n=e/t;1!=n&&(document.documentElement.style.fontSize=e*n+\"px\")}},window.Adapter=new e,window.Adapter.reset(),window.οnlοad=function(){window.Adapter.reset()},window.οnresize=function(){window.Adapter.reset()}}();</script> <meta name=\"screen-orientation\" content=\"portrait\"><meta name=\"x5-orientation\" content=\"portrait\"><script>tac='i)69eo056r4s!i$1afls\"0,<8~z|\x7f@QGNCJF[\\\\^D\\\\KFYSk~^WSZhg,(lfi~ah`{md\"inb|1d<,%Dscafgd\"in,8[xtm}nLzNEGQMKAdGG^NTY\x1ckgd\"inb<b|1d<g,&TboLr{m,(\x02)!jx-2n&vr$testxg,%@tug{mn ,%vrfkbm[!cb|'</script><script type=\"text/javascript\">!function(){function e(e){return this.config=e,this}e.prototype={reset:function(){var e=Math.min(document.documentElement.clientWidth,750)/750*100;document.documentElement.style.fontSize=e+\"px\";var t=parseFloat(window.getComputedStyle(document.documentElement).fontSize),n=e/t;1!=n&&(document.documentElement.style.fontSize=e*n+\"px\")}},window.Adapter=new e,window.Adapter.reset(),window.οnlοad=function(){window.Adapter.reset()},window.οnresize=function(){window.Adapter.reset()}}();</script><meta name=\"pathname\" content=\"aweme_mobile_user\"> <meta name=\"screen-orientation\" content=\"portrait\"><meta name=\"x5-orientation\" content=\"portrait\"><meta name=\"theme-color\" content=\"#161823\"><meta name=\"pathname\" content=\"aweme_mobile_video\"><link rel=\"dns-prefetch\" href=\"//s3.bytecdn.cn/\"><link rel=\"dns-prefetch\" href=\"//s3a.bytecdn.cn/\"><link rel=\"dns-prefetch\" href=\"//s3b.bytecdn.cn/\"><link rel=\"dns-prefetch\" href=\"//s0.pstatp.com/\"><link rel=\"dns-prefetch\" href=\"//s1.pstatp.com/\"><link rel=\"dns-prefetch\" href=\"//s2.pstatp.com/\"><link rel=\"dns-prefetch\" href=\"//v1-dy.ixigua.com/\"><link rel=\"dns-prefetch\" href=\"//v1-dy.ixiguavideo.com/\"><link rel=\"dns-prefetch\" href=\"//v3-dy.ixigua.com/\"><link rel=\"dns-prefetch\" href=\"//v3-dy.ixiguavideo.com/\"><link rel=\"dns-prefetch\" href=\"//v6-dy.ixigua.com/\"><link rel=\"dns-prefetch\" href=\"//v6-dy.ixiguavideo.com/\"><link rel=\"dns-prefetch\" href=\"//v9-dy.ixigua.com/\"><link rel=\"dns-prefetch\" href=\"//v9-dy.ixiguavideo.com/\"><link rel=\"dns-prefetch\" href=\"//v11-dy.ixigua.com/\"><link rel=\"dns-prefetch\" href=\"//v11-dy.ixiguavideo.com/\"><link rel=\"stylesheet\" href=\"//s3.bytecdn.cn/ies/resource/falcon/douyin_falcon/static/style/base_99078a4.css\"><style>@font-face{font-family:iconfont;src:url(//s3a.bytecdn.cn/ies/resource/falcon/douyin_falcon/static/font/iconfont_9eadf2f.eot);src:url(//s3a.bytecdn.cn/ies/resource/falcon/douyin_falcon/static/font/iconfont_9eadf2f.eot#iefix) format('embedded-opentype'),url(//s3.bytecdn.cn/ies/resource/falcon/douyin_falcon/static/font/iconfont_9eb9a50.woff) format('woff'),url(//s3a.bytecdn.cn/ies/resource/falcon/douyin_falcon/static/font/iconfont_da2e2ef.ttf) format('truetype'),url(//s3.bytecdn.cn/ies/resource/falcon/douyin_falcon/static/font/iconfont_31180f7.svg#iconfont) format('svg')}.iconfont{font-family:iconfont!important;font-size:.24rem;font-style:normal;letter-spacing:-.045rem;margin-left:-.085rem}@font-face{font-family:icons;src:url(//s3.bytecdn.cn/ies/resource/falcon/douyin_falcon/static/icons/iconfont_2f1b1cd.eot);src:url(//s3.bytecdn.cn/ies/resource/falcon/douyin_falcon/static/icons/iconfont_2f1b1cd.eot#iefix) format('embedded-opentype'),url(//s3.bytecdn.cn/ies/resource/falcon/douyin_falcon/static/icons/iconfont_87ad39c.woff) format('woff'),url(//s3.bytecdn.cn/ies/resource/falcon/douyin_falcon/static/icons/iconfont_5848858.ttf) format('truetype'),url(//s3a.bytecdn.cn/ies/resource/falcon/douyin_falcon/static/icons/iconfont_20c7f77.svg#iconfont) format('svg')}.icons{font-family:icons!important;font-size:.24rem;font-style:normal;-webkit-font-smoothing:antialiased;-webkit-text-stroke-width:.2px;-moz-osx-font-smoothing:grayscale}@font-face{font-family:Ies;src:url(//s3.bytecdn.cn/ies/resource/falcon/douyin_falcon/static/icons/Ies_317064f.woff2?ba9fc668cd9544e80b6f5998cdce1672) format(\"woff2\"),url(//s3a.bytecdn.cn/ies/resource/falcon/douyin_falcon/static/icons/Ies_a07f3d4.woff?ba9fc668cd9544e80b6f5998cdce1672) format(\"woff\"),url(//s3.bytecdn.cn/ies/resource/falcon/douyin_falcon/static/icons/Ies_4c0d8be.ttf?ba9fc668cd9544e80b6f5998cdce1672) format(\"truetype\"),url(//s3.bytecdn.cn/ies/resource/falcon/douyin_falcon/static/icons/Ies_1ac3f94.svg?ba9fc668cd9544e80b6f5998cdce1672#Ies) format(\"svg\")}i{line-height:1}i[class^=ies-]:before,i[class*=\" ies-\"]:before{font-family:Ies!important;font-style:normal;font-weight:400!important;font-variant:normal;text-transform:none;line-height:1;-webkit-font-smoothing:antialiased;-moz-osx-font-smoothing:grayscale}.ies-checked:before{content:\"\\f101\"}.ies-chevron-left:before{content:\"\\f102\"}.ies-chevron-right:before{content:\"\\f103\"}.ies-clear:before{content:\"\\f104\"}.ies-close:before{content:\"\\f105\"}.ies-copy:before{content:\"\\f106\"}.ies-delete:before{content:\"\\f107\"}.ies-edit:before{content:\"\\f108\"}.ies-help-circle:before{content:\"\\f109\"}.ies-info:before{content:\"\\f10a\"}.ies-loading:before{content:\"\\f10b\"}.ies-location:before{content:\"\\f10c\"}.ies-paste:before{content:\"\\f10d\"}.ies-plus:before{content:\"\\f10e\"}.ies-query:before{content:\"\\f10f\"}.ies-remove:before{content:\"\\f110\"}.ies-search:before{content:\"\\f111\"}.ies-settings:before{content:\"\\f112\"}.ies-shopping-bag:before{content:\"\\f113\"}.ies-sort-left:before{content:\"\\f114\"}.ies-sort-right:before{content:\"\\f115\"}.ies-title-decorate-left:before{content:\"\\f116\"}.ies-title-decorate-right:before{content:\"\\f117\"}.ies-triangle-right:before{content:\"\\f118\"}.ies-triangle-top:before{content:\"\\f119\"}.ies-video:before{content:\"\\f11a\"}</style> <link rel=\"stylesheet\" href=\"//s3a.bytecdn.cn/ies/resource/falcon/douyin_falcon/component/loading/index_5108ff2.css\">\n" + "<link rel=\"stylesheet\" href=\"//s3.bytecdn.cn/ies/resource/falcon/douyin_falcon/component/banner/index_3941ffc.css\">\n" + "<link rel=\"stylesheet\" href=\"//s3a.bytecdn.cn/ies/resource/falcon/douyin_falcon/component/common/openBrowser/index_2c31596.css\">\n" + "<link rel=\"stylesheet\" href=\"//s3a.bytecdn.cn/ies/resource/falcon/douyin_falcon/page/reflow_user/index_ecb0bc9.css\">\n" + "<link rel=\"stylesheet\" href=\"//s3a.bytecdn.cn/ies/resource/falcon/douyin_falcon/pkg/video_93fd288.css\"></head>", i = {}, o = {}, a = {}, u = {}, c = {}, s = {}, l = function (t, n) { if (!(t in u)) { u[t] = !0; var i = document.createElement("script"); if (n) { var o = setTimeout(n, e.timeout); i.onerror = function () { clearTimeout(o), n() } ; var a = function () { clearTimeout(o) }; "onload" in i ? i.onload = a : i.onreadystatechange = function () { ("loaded" === this.readyState || "complete" === this.readyState) && a() } } return i.type = "text/javascript", i.src = t, r.appendChild(i), i } }, f = function (t, e, n) { var r = i[t] || (i[t] = []); r.push(e); var o, a = c[t] || c[t + ".js"] || {}, u = a.pkg; o = u ? s[u].url || s[u].uri : a.url || a.uri || t, l(o, n && function () { n(t) } ) }; n = function (t, e) { "function" != typeof e && (e = arguments[2]), t = t.replace(/\.js$/i, ""), o[t] = e; var n = i[t]; if (n) { for (var r = 0, a = n.length; a > r; r++) n[r](); delete i[t] } } , e = function (t) { if (t && t.splice) return e.async.apply(this, arguments); t = e.alias(t); var n = a[t]; if (n) return n.exports; var r = o[t]; if (!r) throw "[ModJS] Cannot find module `" + t + "`"; n = a[t] = { exports: {} }; var i = "function" == typeof r ? r.apply(n, [e, n.exports, n]) : r; return i && (n.exports = i), n.exports && !n.exports["default"] && Object.defineProperty && Object.isExtensible(n.exports) && Object.defineProperty(n.exports, "default", { value: n.exports }), n.exports } , e.async = function (n, r, i) { function a(t) { for (var n, r = 0, h = t.length; h > r; r++) { var p = e.alias(t[r]); p in o ? (n = c[p] || c[p + ".js"], n && "deps" in n && a(n.deps)) : p in s || (s[p] = !0, l++, f(p, u, i), n = c[p] || c[p + ".js"], n && "deps" in n && a(n.deps)) } } function u() { if (0 === l--) { for (var i = [], o = 0, a = n.length; a > o; o++) i[o] = e(n[o]); r && r.apply(t, i) } } "string" == typeof n && (n = [n]); var s = {} , l = 0; a(n), u() } , e.resourceMap = function (t) { var e, n; n = t.res; for (e in n) n.hasOwnProperty(e) && (c[e] = n[e]); n = t.pkg; for (e in n) n.hasOwnProperty(e) && (s[e] = n[e]) } , e.loadJs = function (t) { l(t) } , e.loadCss = function (t) { if (t.content) { var e = document.createElement("style"); e.type = "text/css", e.styleSheet ? e.styleSheet.cssText = t.content : e.innerHTML = t.content, r.appendChild(e) } else if (t.url) { var n = document.createElement("link"); n.href = t.url, n.rel = "stylesheet", n.type = "text/css", r.appendChild(n) } } , e.alias = function (t) { return t.replace(/\.js$/i, "") } , e.timeout = 5e3, t.__M.define = n, t.__M.require = e } }(this) this.__M.define("douyin_falcon:node_modules/byted-acrawler/dist/runtime", function (l, e) { Function(function (l) { return 'e(e,a,r){(b[e]||(b[e]=t("x,y","x "+e+" y")(r,a)}a(e,a,r){(k[r]||(k[r]=t("x,y","new x[y]("+Array(r+1).join(",x[y]")(1)+")")(e,a)}r(e,a,r){n,t,s={},b=s.d=r?r.d+1:0;for(s["$"+b]=s,t=0;t<b;t)s[n="$"+t]=r[n];for(t=0,b=s=a;t<b;t)s[t]=a[t];c(e,0,s)}c(t,b,k){u(e){v[x]=e}f{g=,ting(bg)}l{try{y=c(t,b,k)}catch(e){h=e,y=l}}for(h,y,d,g,v=[],x=0;;)switch(g=){case 1:u(!)4:f5:u((e){a=0,r=e;{c=a<r;c&&u(e[a]),c}}(6:y=,u((y8:if(g=,lg,g=,y===c)b+=g;else if(y!==l)y9:c10:u(s(11:y=,u(+y)12:for(y=f,d=[],g=0;g<y;g)d[g]=y.charCodeAt(g)^g+y;u(String.fromCharCode.apply(null,d13:y=,h=delete [y]14:59:u((g=)?(y=x,v.slice(x-=g,y:[])61:u([])62:g=,k[0]=65599*k[0]+k[1].charCodeAt(g)>>>065:h=,y=,[y]=h66:u(e(t[b],,67:y=,d=,u((g=).x===c?r(g.y,y,k):g.apply(d,y68:u(e((g=t[b])<"<"?(b--,f):g+g,,70:u(!1)71:n72:+f73:u(parseInt(f,3675:if(){bcase 74:g=<<16>>16g76:u(k[])77:y=,u([y])78:g=,u(a(v,x-=g+1,g79:g=,u(k["$"+g])81:h=,[f]=h82:u([f])83:h=,k[]=h84:!085:void 086:u(v[x-1])88:h=,y=,h,y89:u({e{r(e.y,arguments,k)}e.y=f,e.x=c,e})90:null91:h93:h=0:;default:u((g<<16>>16)-16)}}n=this,t=n.Function,s=Object.keys||(e){a={},r=0;for(c in e)a[r]=c;a=r,a},b={},k={};r'.replace(/[-]/g, function (e) { return l[15 & e.charCodeAt(0)] }) }("v[x++]=v[--x]t.charCodeAt(b++)-32function return ))++.substrvar .length(),b+=;break;case ;break}".split("")))()('gr$Daten Иb/s!l y͒yĹg,(lfi~ah`{mv,-n|jqewVxp{rvmmx,&effkx[!cs"l".Pq%widthl"@q&heightl"vr*getContextx$"2d[!cs#l#,*;?|u.|uc{uq$fontl#vr(fillTextx$$龘ฑภ경2<[#c}l#2q*shadowBlurl#1q-shadowOffsetXl#$$limeq+shadowColorl#vr#arcx88802[%c}l#vr&strokex[ c}l"v,)}eOmyoZB]mx[ cs!0s$l$Pb<k7l l!r&lengthb%^l$1+s$jl s#i$1ek1s$gr#tack4)zgr#tac$! +0o![#cj?o ]!l$b%s"o ]!l"l$b*b^0d#>>>s!0s%yA0s"l"l!r&lengthb<k+l"^l"1+s"jl s&l&z0l!$ +["cs\'(0l#i\'1ps9wxb&s() &{s)/s(gr&Stringr,fromCharCodes)0s*yWl ._b&s o!])l l Jb<k$.aj;l .Tb<k$.gj/l .^b<k&i"-4j!+& s+yPo!]+s!l!l Hd>&l!l Bd>&+l!l <d>&+l!l 6d>&+l!l &+ s,y=o!o!]/q"13o!l q"10o!],l 2d>& s.{s-yMo!o!]0q"13o!]*Ld<l 4d#>>>b|s!o!l q"10o!],l!& s/yIo!o!].q"13o!],o!]*Jd<l 6d#>>>b|&o!]+l &+ s0l-l!&l-l!i\'1z141z4b/@d<l"b|&+l-l(l!b^&+l-l&zl\'g,)gk}ejo{cm,)|yn~Lij~em["cl$b%@d<l&zl\'l $ +["cl$b%b|&+l-l%8d<@b|l!b^&+ q$sign ', [Object.defineProperty(e, "__esModule", {value: !0})]) }); _bytedAcrawler = this.__M.require("douyin_falcon:node_modules/byted-acrawler/dist/runtime"); signature = _bytedAcrawler.sign(process.argv[2]) console.log(signature);
import requests
user_id = '58841646784' # 6556303280
# 获取小姐姐的所有作品
"""
signature = _bytedAcrawler.sign('用户ID')
douyin_falcon:node_modules/byted-acrawler/dist/runtime
"""
import subprocess
signature = subprocess.getoutput('node s1.js %s' %user_id)
user_video_list = []
# ############################# 获取个人作品 ##########################
user_video_params = {
'user_id': str(user_id),
'count': '21',
'max_cursor': '0',
'aid': '1128',
'_signature': signature,
'dytk': 'b4dceed99803a04a1c4395ffc81f3dbc' # '114f1984d1917343ccfb14d94e7ce5f5'
}
def get_aweme_list(max_cursor=None):
if max_cursor:
user_video_params['max_cursor'] = str(max_cursor)
res = requests.get(
url="https://www.douyin.com/aweme/v1/aweme/post/",
params=user_video_params,
headers={
'user-agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36',
'x-requested-with':'XMLHttpRequest',
'referer':'https://www.douyin.com/share/user/58841646784',
}
)
content_json = res.json()
aweme_list = content_json.get('aweme_list', [])
user_video_list.extend(aweme_list)
if content_json.get('has_more') == 1:
return get_aweme_list(content_json.get('max_cursor'))
get_aweme_list()
# ############################# 获取喜欢作品 ##########################
favor_video_list = []
favor_video_params = {
'user_id': str(user_id),
'count': '21',
'max_cursor': '0',
'aid': '1128',
'_signature': signature,
'dytk': 'b4dceed99803a04a1c4395ffc81f3dbc'
}
def get_favor_list(max_cursor=None):
if max_cursor:
favor_video_params['max_cursor'] = str(max_cursor)
res = requests.get(
url="https://www.douyin.com/aweme/v1/aweme/favorite/",
params=favor_video_params,
headers={
'user-agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36',
'x-requested-with':'XMLHttpRequest',
'referer':'https://www.douyin.com/share/user/58841646784',
}
)
content_json = res.json()
aweme_list = content_json.get('aweme_list', [])
favor_video_list.extend(aweme_list)
if content_json.get('has_more') == 1:
return get_favor_list(content_json.get('max_cursor'))
get_favor_list()
# ############################# 视频下载 ##########################
for item in user_video_list:
video_id = item['video']['play_addr']['uri']
video = requests.get(
url='https://aweme.snssdk.com/aweme/v1/playwm/',
params={
'video_id':video_id
},
headers={
'user-agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36',
'x-requested-with': 'XMLHttpRequest',
'referer': 'https://www.douyin.com/share/user/58841646784',
},
stream=True
)
file_name = video_id + '.mp4'
with open(file_name,'wb') as f:
for line in video.iter_content():
f.write(line)
for item in favor_video_list:
video_id = item['video']['play_addr']['uri']
video = requests.get(
url='https://aweme.snssdk.com/aweme/v1/playwm/',
params={
'video_id':video_id
},
headers={
'user-agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36',
'x-requested-with': 'XMLHttpRequest',
'referer': 'https://www.douyin.com/share/user/58841646784',
},
stream=True
)
file_name = video_id + '.mp4'
with open(file_name, 'wb') as f:
for line in video.iter_content():
f.write(line)
2241
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
