Feature
Nested web page, to switch to the sub-frame iframe, then further action
method
browser.switch_to.iframe(iframe_element)
Example - Login qq-mail
from selenium import webdriver import time driver = webdriver.Chrome() driver.get('https://mail.qq.com/') # Switch to the sub-frame iframe login_frame = driver.find_element_by_id ( ' login_frame ' ) driver.switch_to.frame(login_frame) # Username + Password + Log driver.find_element_by_id ( ' U ' ) .send_keys ( ' 2621470058 ' ) driver.find_element_by_id ( ' P ' ) .send_keys ( ' password ' ) driver.find_element_by_id('login_button').click() # Reservation page record time the time.sleep (5 ) # Extracted data ELE = driver.find_element_by_id ( ' USERALIAS ' ) Print (ele.text)
1, POST Address: https://fanyi.baidu.com/ v2transapi 2 , Form1 form data (multiple gripping changing fields) from : ZH two: one Sign: 54706.276099 # This is how to generate? token: a927248ae7146c842bb4a94457ca35ee # basic fixed, but also to find ways to get
2 to crawl the JS file
The upper right corner - search - sign: - find a specific JS file (index_c8a141d.js) - formatted output
3, to find a sign of the generated code in the JS
1 , in the search of the formatted output JS code: sign: JS code found as follows: sign: m (a), 2 , by setting breakpoints, locate the m (a) function, i.e. a function of generating a specific sign # 1 the word to be translated as a # 2 at the position of the mouse to move to m (a), a click-to DETAILED m (a) function block
4, the generated sign m (a) as a function of the specific code (in a large define)
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) { a var = ocharAt (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) { was 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 = "" + the String.fromCharCode (103) + the String.fromCharCode (1 16) + the String.fromCharCode (107 ); // == null = U I I: (I!? window = [L] || "" ) || "" ; // breakpoints, then locate the value from the web page source code window.gtk 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, directly to the local code into js file, using module executed pyexecjs js code debugging
Installation pyexecjs module
sudo pip3 install pyexecjs
import execjs with open('node.js','r') as f: js_data = f.read () # create the object exec_object = execjs.compile (js_data) sign = exec_object.eval('e("hello")') print(sign)
Get token
# In the js token: window.common.token # in response to find ways to get this value TOKEN_URL = ' https://fanyi.baidu.com/?aldtype=16047 ' regex: " token: '(.? *)' "
Specific code implementation
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': '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 ' # defined request header R & lt 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] # Gets Sign DEF get_sign (Self, Word): Open with ( ' Baidu translation .js ' , ' R & lt ' ) AS F: js_data = f.read() exec_object = execjs.compile(js_data) sign = exec_object.eval('e("{}")'.format(word)) return sign # Main function DEF main (Self, Word, FRO, to): token,gtk = self.get_token() Sign = self.get_sign (Word) # find form as the form data, sign and token need to find ways obtain 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. 2. Translation English to Chinese English ' Choice = INPUT ( ' 1. 2. English to Chinese English Translation: ' ) Word = the INPUT ( ' Enter word to be translated: ' ) IF Choice == ' 1 ' : fro,to = 'en','zh' elif choice == '2': fro, to = ' zh ' , ' en ' spider.main(word,fro,to)