首先：看看运行结果效果如何！
小编基本实现思路如下：
我们看一下上述这个网址的请求方式以及请求参数。
显然这个signKey 进行了加密处理。（下面请求第二点讲解怎样模拟这个请求）
我们点击启动器下如图所示的链接，来到如下界面，对这个界面下的js代码进行断点和监听，如下：
是不是发现了熟悉的身影，就是 x 变量里面的参数值是不是和小编在上述所说的get请求参数很像。
我们点击其中自定义方法i[_0xe30b("0x5")])，点击进入，然后打上断点，刷新界面之后继续监听，发现如下：
现在继续点击方法 r[a(_0x193d("0xe4"))] 进入，发现如下
其实方法 r[a(_0x193d("0xe4"))] 就是这个 x[_0x193d("0x6")] 方法，你可别看它们两的值不一样，但是 r[a(_0x193d("0xe4"))] 就是这个 x[_0x193d("0x6")] ,再也找不到第二个了。
接下来就要继续在这个方法下点击已经定义好的方法进入，然后断点，刷新和监听，重复动作，小编就不一一讲解了。
小编把本次程序中需要用到的js代码放到如下，可能和读者自己操作看到的一些js代码不一样哈！(改了一些，另外，就是猫眼电影网址那个js加密字段代码已经更新了)
var getMD5Sign = function (x) { var c = x['method'], e = x['channelId'], _ = void 0 === e ? 40011 : e, t = x['sVersion'], n = x['type'], a = void 0 === n ? "qs" : n, i = Math['ceil'](10 * Math.random()), d = (new Date)['getTime'](), s = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.71 Safari/537.36', u = 'method=' + c + '&timeStamp=' + d + '&User-Agent=' + s + '&index=' + i + '&channelId=' + _ + '&sVersion=' + t; f = '&key=A013F70DB97834C0A5492378BD76C53A'; return { randomNum: i, timeStamp: d, md5sign: default2(u + f), channelId: _, sVersion: t, params: {webdriver: false} }};var default2 = function (x) { if (void 0 === x || null === x) throw new Error(x); var _ = wordsToBytes(a(x)); return bytesToHex(_);};var _ff = function (x, c, e, _, t, n, a) { var r = x + (c & e | ~c & _) + (t >>> 0) + a; return (r << n | r >>> 32 - n) + c};var _gg = function (x, c, e, _, t, n, a) { var r = x + (c & _ | e & ~_) + (t >>> 0) + a; return (r << n | r >>> 32 - n) + c};var _hh = function (x, c, e, _, t, n, a) { var r = x + (c ^ e ^ _) + (t >>> 0) + a; return (r << n | r >>> 32 - n) + c};var _ii = function (x, c, e, _, t, n, a) { var r = x + (e ^ (c | ~_)) + (t >>> 0) + a; return (r << n | r >>> 32 - n) + c};var a = function (x) { x = stringToBytes(x); // x['constructor'] == String ? x = e && e['encoding'] === 'binary' ? stringToBytes(x) : stringToBytes(x) : t(x) ? x = Array.prototype.slice.call(x, 0) : Array['isArray'](x) || x.constructor === Uint8Array || (x = x['toString']()); for (var r = bytesToWords(x), i = 8 * x['length'], d = 1732584193, s = -271733879, o = -1732584194, u = 271733878, f = 0; f < r['length']; f++) r[f] = 16711935 & (r[f] << 8 | r[f] >>> 24) | 4278255360 & (r[f] << 24 | r[f] >>> 8); r[i >>> 5] |= 128 << i % 32, r[14 + (i + 64 >>> 9 << 4)] = i; for (var l = _ff, m = _gg, h = _hh, b = _ii, f = 0; f < r.length; f += 16) { var y = d, p = s, L = o, M = u; d = l(d, s, o, u, r[f + 0], 7, -680876936), u = l(u, d, s, o, r[f + 1], 12, -389564586), o = l(o, u, d, s, r[f + 2], 17, 606105819), s = l(s, o, u, d, r[f + 3], 22, -1044525330), d = l(d, s, o, u, r[f + 4], 7, -176418897), u = l(u, d, s, o, r[f + 5], 12, 1200080426), o = l(o, u, d, s, r[f + 6], 17, -1473231341), s = l(s, o, u, d, r[f + 7], 22, -45705983), d = l(d, s, o, u, r[f + 8], 7, 1770035416), u = l(u, d, s, o, r[f + 9], 12, -1958414417), o = l(o, u, d, s, r[f + 10], 17, -42063), s = l(s, o, u, d, r[f + 11], 22, -1990404162), d = l(d, s, o, u, r[f + 12], 7, 1804603682), u = l(u, d, s, o, r[f + 13], 12, -40341101), o = l(o, u, d, s, r[f + 14], 17, -1502002290), s = l(s, o, u, d, r[f + 15], 22, 1236535329), d = m(d, s, o, u, r[f + 1], 5, -165796510), u = m(u, d, s, o, r[f + 6], 9, -1069501632), o = m(o, u, d, s, r[f + 11], 14, 643717713), s = m(s, o, u, d, r[f + 0], 20, -373897302), d = m(d, s, o, u, r[f + 5], 5, -701558691), u = m(u, d, s, o, r[f + 10], 9, 38016083), o = m(o, u, d, s, r[f + 15], 14, -660478335), s = m(s, o, u, d, r[f + 4], 20, -405537848), d = m(d, s, o, u, r[f + 9], 5, 568446438), u = m(u, d, s, o, r[f + 14], 9, -1019803690), o = m(o, u, d, s, r[f + 3], 14, -187363961), s = m(s, o, u, d, r[f + 8], 20, 1163531501), d = m(d, s, o, u, r[f + 13], 5, -1444681467), u = m(u, d, s, o, r[f + 2], 9, -51403784), o = m(o, u, d, s, r[f + 7], 14, 1735328473), s = m(s, o, u, d, r[f + 12], 20, -1926607734), d = h(d, s, o, u, r[f + 5], 4, -378558), u = h(u, d, s, o, r[f + 8], 11, -2022574463), o = h(o, u, d, s, r[f + 11], 16, 1839030562), s = h(s, o, u, d, r[f + 14], 23, -35309556), d = h(d, s, o, u, r[f + 1], 4, -1530992060), u = h(u, d, s, o, r[f + 4], 11, 1272893353), o = h(o, u, d, s, r[f + 7], 16, -155497632), s = h(s, o, u, d, r[f + 10], 23, -1094730640), d = h(d, s, o, u, r[f + 13], 4, 681279174), u = h(u, d, s, o, r[f + 0], 11, -358537222), o = h(o, u, d, s, r[f + 3], 16, -722521979), s = h(s, o, u, d, r[f + 6], 23, 76029189), d = h(d, s, o, u, r[f + 9], 4, -640364487), u = h(u, d, s, o, r[f + 12], 11, -421815835), o = h(o, u, d, s, r[f + 15], 16, 530742520), s = h(s, o, u, d, r[f + 2], 23, -995338651), d = b(d, s, o, u, r[f + 0], 6, -198630844), u = b(u, d, s, o, r[f + 7], 10, 1126891415), o = b(o, u, d, s, r[f + 14], 15, -1416354905), s = b(s, o, u, d, r[f + 5], 21, -57434055), d = b(d, s, o, u, r[f + 12], 6, 1700485571), u = b(u, d, s, o, r[f + 3], 10, -1894986606), o = b(o, u, d, s, r[f + 10], 15, -1051523), s = b(s, o, u, d, r[f + 1], 21, -2054922799), d = b(d, s, o, u, r[f + 8], 6, 1873313359), u = b(u, d, s, o, r[f + 15], 10, -30611744), o = b(o, u, d, s, r[f + 6], 15, -1560198380), s = b(s, o, u, d, r[f + 13], 21, 1309151649), d = b(d, s, o, u, r[f + 4], 6, -145523070), u = b(u, d, s, o, r[f + 11], 10, -1120210379), o = b(o, u, d, s, r[f + 2], 15, 718787259), s = b(s, o, u, d, r[f + 9], 21, -343485551), d = d + y >>> 0, s = s + p >>> 0, o = o + L >>> 0, u = u + M >>> 0 } return endian([d, s, o, u]);};var rotl = function (x, c) { return x << c | x >>> 32 - c;};var rotr = function (x, c) { return x << 32 - c | x >>> c;};var endian = function (x) { if (x['constructor'] == Number) return 16711935 & rotl(x, 8) | 4278255360 & rotl(x, 24); for (var c = 0; c < x['length']; c++) x[c] = endian(x[c]); return x};var bytesToWords = function (x) { for (var c = [], e = 0, _ = 0; e < x['length']; e++, _ += 8) c[_ >>> 5] |= x[e] << 24 - _ % 32; return c};var wordsToBytes = function (x) { for (var c = [], e = 0; e < 32 * x['length']; e += 8) c['push'](x[e >>> 5] >>> 24 - e % 32 & 255); return c};var stringToBytes = function (x) { for (var c = [], e = 0; e < x.length; e++) c['push'](255 & x.charCodeAt(e)); return c;};var bytesToHex = function (x) { for (var c = [], e = 0; e < x.length; e++) c['push']((x[e] >>> 4)['toString'](16)), c['push']((15 & x[e])['toString'](16)); return c['join']("")};文件名：common.js
这里主要运用模块pytesseract对如下图片进行识别，从而得到加密字段对应的原字段信息。当然需要下载tesseract.exe
为了提高识别的正确率，小编运用cv2对这些图片进行截取处理。
参考代码如下：
from PIL import Imageimport pytesseractimport cv2import timeimg = cv2.imread(filename='./input.png')imgInfo = img.shapex_1 = 0x_2 = 125font_dict = {}for i in range(12): dst = img[:,x_1:x_2] x_1 = x_2 x_2 += 125 dst2 = dst[6:100,15:120] dst3 = dst[105:148,15:111] cv2.imwrite(filename='1.png',img=dst2) cv2.imwrite(filename='2.png',img=dst3) time.sleep(1) text2 = pytesseract.image_to_string(Image.open(fp='1.png'), config='--psm 10 --oem 3 -c tessedit_char_whitelist=0123456789') text3 = pytesseract.image_to_string(Image.open(fp='2.png'),lang='eng',config='--psm 6') if text2.strip() != '': text31 = text3.strip() font_dict[text2.strip()] = (text31.split('\n')[0]).lower().replace('$',r'\u')print(font_dict)
不过,这个识别的正确率还是有待提高的，不过我们可以通过其他一些代码进行处理，尽量提高它的正确度。
import requestsimport reimport execjsfrom selenium import webdriverfrom lxml import etreefrom PIL import Image, ImageGrabimport pytesseractimport timeimport cv2main_url = input('请输入猫眼电影网址：')movie_id = re.findall('https://www.maoyan.com/films/(.*)', main_url)[0]url = 'https://www.maoyan.com/ajax/films/%s' % (movie_id)with open(file='./common.js', mode='r', encoding='utf-8') as f: js = f.read()ctx = execjs.compile(js) # 执行js代码flag = { 'method': 'GET', 'channelId': 40011, 'sVersion': 1, 'type': 'object'}n = ctx.call('getMD5Sign', flag)e = n['randomNum']i = n['timeStamp']o = n['md5sign']c = n['channelId']s = n['sVersion']# _ = n['params']params = { 'index': e, 'timeStamp': i, 'signKey': o, 'channelId': c, 'sVersion': s, 'webdriver': 'false'}headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.71 Safari/537.36'}rsp = requests.get(url=url, params=params, headers=headers)print('请求状态码为：', rsp.status_code)font_dict = {}infos = []if len((rsp.text).strip()) == 0: passelse: html = rsp.text woff_href = re.findall("url('(.*?)') format('woff');", html)[0] # woff文件下载链接 woff_url = 'http:' + woff_href # woff文件的下载链接 html2 = etree.HTML(html) infos = html2.xpath("//div[@class='movie-stats-container']//span[@class='stonefont']/text()") # 评分等信息 driver = webdriver.Chrome() driver.get(url='https://font.qqe2.com/') driver.implicitly_wait(15) driver.maximize_window() # 最大窗口 ele = driver.find_elements_by_xpath("//button[@class='btn btn-flat btn-sm dropdown-toggle']")[0] # 导入按钮 ele.click() # 点击 ele2 = driver.find_element_by_xpath("//ul[@class='dropdown-menu']/li[@data-action='add-url']") # 点击从url上加载字体 ele2.click() ele3 = driver.find_elements_by_xpath("//input[@class='form-control']")[1] # 输入框 ele3.send_keys(woff_url) ele4 = driver.find_element_by_xpath("//button[@class='btn btn-flat btn-sm btn-confirm']") ele4.click() # 确认按钮 time.sleep(5) bbox = (236, 278, 1502 + 236, 164 + 278) img = ImageGrab.grab(bbox) img.save('input.png') driver.close() img = cv2.imread(filename='./input.png') imgInfo = img.shape x_1 = 0 x_2 = 125 for i in range(12): dst = img[:, x_1:x_2] x_1 = x_2 x_2 += 125 dst2 = dst[6:100, 15:120] dst3 = dst[105:148, 10:111] cv2.imwrite(filename='1.png', img=dst2) cv2.imwrite(filename='2.png', img=dst3) time.sleep(1) text2 = pytesseract.image_to_string(Image.open(fp='1.png'), config='--psm 10 --oem 3 -c tessedit_char_whitelist=0123456789') text3 = pytesseract.image_to_string(Image.open(fp='2.png'),lang='eng',config='--psm 6') if text2.strip() != '': text31 = text3.strip() font_dict[text2.strip()] = (text31.split('\n')[1]).lower().replace('uni', r'\u').replace('.','').replace(',','').replace('-','')print('字体对应关系如下：')print(font_dict)print(infos)mains_list = []for i in range(len(infos)): infos[i] = infos[i].encode('unicode_escape').decode('utf-8') lists_u = [] index = 0 while index < len(infos[i])//6: str_u = infos[i][index*6:(index+1)*6] if '.' in str_u: lists_u.append('.') infos[i] = infos[i].replace('.','') str_u = infos[i][index * 6:(index + 1) * 6] lists_u.append(str_u) else: lists_u.append(str_u) index += 1 mains_list.append(lists_u)for i in range(len(mains_list)): for j in range(len(mains_list[i])): str_u2 = mains_list[i][j] if str_u2 != '.': bool_u = False for key in font_dict: str_u3 = font_dict[key] if str_u3 == str_u2: mains_list[i][j] = key bool_u = True if not bool_u: for key in font_dict: str_u3 = font_dict[key] error = 0 for k in range(len(str_u3)): if str_u3[k] != str_u2[k]: if str_u3[k] == 's' and str_u2[k] == '5': pass else: error += 1 if error == 0 or error ==1: mains_list[i][j] = keyprint(mains_list)for i in range(len(mains_list)): mains_list[i] = ''.join(mains_list[i])print(mains_list)