selenium - iframe子框架
特点
网页中嵌套了网页，先切换到iframe子框架，然后再执行其他操作
方法
browser.switch_to.iframe(iframe_element)
示例 - 登录qq邮箱
from selenium import webdriver import time driver = webdriver.Chrome() driver.get('https://mail.qq.com/') # 切换到iframe子框架 login_frame = driver.find_element_by_id('login_frame') driver.switch_to.frame(login_frame) # 用户名+密码+登录 driver.find_element_by_id('u').send_keys('2621470058') driver.find_element_by_id('p').send_keys('密码') driver.find_element_by_id('login_button').click() # 预留页面记载时间 time.sleep(5) # 提取数据 ele = driver.find_element_by_id('useralias') print(ele.text)
1、POST地址: https://fanyi.baidu.com/v2transapi 2、Form表单数据（多次抓取在变的字段） from: zh to: en sign: 54706.276099 #这个是如何生成的？ token: a927248ae7146c842bb4a94457ca35ee # 基本固定,但也想办法获取
2抓取相关JS文件
右上角 - 搜索 - sign: - 找到具体JS文件(index_c8a141d.js) - 格式化输出
3、在JS中寻找sign的生成代码
1、在格式化输出的JS代码中搜索: sign: 找到如下JS代码：sign: m(a), 2、通过设置断点，找到m(a)函数的位置，即生成sign的具体函数 # 1. a 为要翻译的单词 # 2. 鼠标移动到 m(a) 位置处，点击可进入具体m(a)函数代码块
4、生成sign的m(a)函数具体代码如下(在一个大的define中)
function a(r) { if (Array.isArray(r)) { for (var o = 0, t = Array(r.length); o < r.length; o++) t[o] = r[o]; return t } return Array.from(r) } function n(r, o) { for (var t = 0; t < o.length - 2; t += 3) { var a = o.charAt(t + 2); a = a >= "a" ? a.charCodeAt(0) - 87 : Number(a), a = "+" === o.charAt(t + 1) ? r >>> a : r << a, r = "+" === o.charAt(t) ? r + a & 4294967295 : r ^ a } return r } function e(r) { var o = r.match(/[\uD800-\uDBFF][\uDC00-\uDFFF]/g); if (null === o) { var t = r.length; t > 30 && (r = "" + r.substr(0, 10) + r.substr(Math.floor(t / 2) - 5, 10) + r.substr(-10, 10)) } else { for (var e = r.split(/[\uD800-\uDBFF][\uDC00-\uDFFF]/), C = 0, h = e.length, f = []; h > C; C++) "" !== e[C] && f.push.apply(f, a(e[C].split(""))), C !== h - 1 && f.push(o[C]); var g = f.length; g > 30 && (r = f.slice(0, 10).join("") + f.slice(Math.floor(g / 2) - 5, Math.floor(g / 2) + 5).join("") + f.slice(-10).join("")) } // var u = void 0 // , l = "" + String.fromCharCode(103) + String.fromCharCode(116) + String.fromCharCode(107); // u = null !== i ? i : (i = window[l] || "") || ""; // 断点调试,然后从网页源码中找到 window.gtk的值 var u = '320305.131321201' for (var d = u.split("."), m = Number(d[0]) || 0, s = Number(d[1]) || 0, S = [], c = 0, v = 0; v < r.length; v++) { var A = r.charCodeAt(v); 128 > A ? S[c++] = A : (2048 > A ? S[c++] = A >> 6 | 192 : (55296 === (64512 & A) && v + 1 < r.length && 56320 === (64512 & r.charCodeAt(v + 1)) ? (A = 65536 + ((1023 & A) << 10) + (1023 & r.charCodeAt(++v)), S[c++] = A >> 18 | 240, S[c++] = A >> 12 & 63 | 128) : S[c++] = A >> 12 | 224, S[c++] = A >> 6 & 63 | 128), S[c++] = 63 & A | 128) } for (var p = m, F = "" + String.fromCharCode(43) + String.fromCharCode(45) + String.fromCharCode(97) + ("" + String.fromCharCode(94) + String.fromCharCode(43) + String.fromCharCode(54)), D = "" + String.fromCharCode(43) + String.fromCharCode(45) + String.fromCharCode(51) + ("" + String.fromCharCode(94) + String.fromCharCode(43) + String.fromCharCode(98)) + ("" + String.fromCharCode(43) + String.fromCharCode(45) + String.fromCharCode(102)), b = 0; b < S.length; b++) p += S[b], p = n(p, F); return p = n(p, D), p ^= s, 0 > p && (p = (2147483647 & p) + 2147483648), p %= 1e6, p.toString() + "." + (p ^ m) }
5、直接将代码写入本地js文件,利用pyexecjs模块执行js代码进行调试
安装 pyexecjs模块
sudo pip3 install pyexecjs
import execjs with open('node.js','r') as f: js_data = f.read() # 创建对象 exec_object = execjs.compile(js_data) sign = exec_object.eval('e("hello")') print(sign)
获取token
# 在js中 token: window.common.token # 在响应中想办法获取此值 token_url = 'https://fanyi.baidu.com/?aldtype=16047' regex: "token: '(.*?)'"
具体代码实现
import requests import re import execjs class BaiduTranslateSpider(object): def __init__(self): self.token_url = 'https://fanyi.baidu.com/?aldtype=16047' self.post_url = 'https://fanyi.baidu.com/v2transapi' self.headers = { 'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3', # 'accept-encoding': 'gzip, deflate, br', 'accept-language': 'zh-CN,zh;q=0.9', 'cache-control': 'no-cache', 'cookie': 'BAIDUID=52920E829C1F64EE98183B703F4E37A9:FG=1; BIDUPSID=52920E829C1F64EE98183B703F4E37A9; PSTM=1562657403; to_lang_often=%5B%7B%22value%22%3A%22en%22%2C%22text%22%3A%22%u82F1%u8BED%22%7D%2C%7B%22value%22%3A%22zh%22%2C%22text%22%3A%22%u4E2D%u6587%22%7D%5D; REALTIME_TRANS_SWITCH=1; FANYI_WORD_SWITCH=1; HISTORY_SWITCH=1; SOUND_SPD_SWITCH=1; SOUND_PREFER_SWITCH=1; delPer=0; BDORZ=B490B5EBF6F3CD402E515D22BCDA1598; BCLID=6890774803653935935; BDSFRCVID=4XAsJeCCxG3DLCbwbJrKDGwjNA0UN_I3KhXZ3J; H_BDCLCKID_SF=tRk8oIDaJCvSe6r1MtQ_M4F_qxby26nUQ5neaJ5n0-nnhnL4W46bqJKFLtozKMoI3C7fotJJ5nololIRy6CKjjb-jaDqJ5n3bTnjstcS2RREHJrg-trSMDCShGRGWlO9WDTm_D_KfxnkOnc6qJj0-jjXqqo8K5Ljaa5n-pPKKRAaqD04bPbZL4DdMa7HLtAO3mkjbnczfn02OP5P5lJ_e-4syPRG2xRnWIvrKfA-b4ncjRcTehoM3xI8LNj405OTt2LEoDPMJKIbMI_rMbbfhKC3hqJfaI62aKDs_RCMBhcqEIL4eJOIb6_w5gcq0T_HttjtXR0atn7ZSMbSj4Qo5pK95p38bxnDK2rQLb5zah5nhMJS3j7JDMP0-4rJhxby523i5J6vQpnJ8hQ3DRoWXPIqbN7P-p5Z5mAqKl0MLIOkbC_6j5DWDTvLeU7J-n8XbI60XRj85-ohHJrFMtQ_q4tehHRMBUo9WDTm_DoTttt5fUj6qJj855jXqqo8KMtHJaFf-pPKKRAashnzWjrkqqOQ5pj-WnQr3mkjbn5yfn02OpjPX6joht4syPRG2xRnWIvrKfA-b4ncjRcTehoM3xI8LNj405OTt2LEoC0XtIDhMDvPMCTSMt_HMxrKetJyaR0JhpjbWJ5TEPnjDUOdLPDW-46HBM3xbKQw5CJGBf7zhpvdWhC5y6ISKx-_J68Dtf5; ZD_ENTRY=baidu; PSINO=2; H_PS_PSSID=26525_1444_21095_29578_29521_28518_29098_29568_28830_29221_26350_29459; locale=zh; Hm_lvt_64ecd82404c51e03dc91cb9e8c025574=1563426293,1563996067; from_lang_often=%5B%7B%22value%22%3A%22zh%22%2C%22text%22%3A%22%u4E2D%u6587%22%7D%2C%7B%22value%22%3A%22en%22%2C%22text%22%3A%22%u82F1%u8BED%22%7D%5D; Hm_lpvt_64ecd82404c51e03dc91cb9e8c025574=1563999768; yjs_js_security_passport=2706b5b03983b8fa12fe756b8e4a08b98fb43022_1563999769_js', 'pragma': 'no-cache', 'upgrade-insecure-requests': '1', 'user-agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.142 Safari/537.36', } # 获取token def get_token(self): token_url = 'https://fanyi.baidu.com/?aldtype=16047' # 定义请求头 r = requests.get(self.token_url,headers=self.headers) token = re.findall(r"token: '(.*?)'",r.text) window_gtk = re.findall(r"window.*?gtk = '(.*?)';</script>",r.text) if token: return token[0],window_gtk[0] # 获取sign def get_sign(self,word): with open('百度翻译.js','r') as f: js_data = f.read() exec_object = execjs.compile(js_data) sign = exec_object.eval('e("{}")'.format(word)) return sign # 主函数 def main(self,word,fro,to): token,gtk = self.get_token() sign = self.get_sign(word) # 找到form表单数据如下,sign和token需要想办法获取 form_data = { 'from': fro, 'to': to, 'query': word, 'transtype': 'realtime', 'simple_means_flag': '3', 'sign': sign, 'token': token } r = requests.post(self.post_url,data=form_data,headers=self.headers) print(r.json()['trans_result']['data'][0]['dst']) if __name__ == '__main__': spider = BaiduTranslateSpider() menu = '1. 英译汉 2. 汉译英' choice = input('1. 英译汉 2. 汉译英 : ') word = input('请输入要翻译的单词:') if choice == '1': fro,to = 'en','zh' elif choice == '2': fro,to = 'zh','en' spider.main(word,fro,to)
