python圖片驗證碼識別最新模組muggle_ocr的示例程式碼
阿新 • • 發佈:2020-07-05
一.官方文件
https://pypi.org/project/muggle-ocr/
二模組安裝
pip install muggle-ocr # 因模組過新,阿里/清華等第三方源可能尚未更新映象,因此手動指定使用境外源,為了提高依賴的安裝速度,可預先自行安裝依賴:tensorflow/numpy/opencv-python/pillow/pyyaml
三.使用程式碼
# 匯入包 import muggle_ocr # 初始化;model_type 包含了 ModelType.OCR/ModelType.Captcha 兩種 sdk = muggle_ocr.SDK(model_type=muggle_ocr.ModelType.OCR) # ModelType.OCR 可識別光學印刷文字 這裡個人覺得應該是官方文件寫錯了 官方文件是ModelType.Captcha 可識別光學印刷文字 with open(r"test1.png","rb") as f: b = f.read() text = sdk.predict(image_bytes=b) print(text) # ModelType.Captcha 可識別4-6位驗證碼 sdk = muggle_ocr.SDK(model_type=muggle_ocr.ModelType.Captcha) with open(r"test1.png","rb") as f: b = f.read() text = sdk.predict(image_bytes=b) print(text)
PS:下面看下 Python 實現全自動登入(真正的全自動,自動識別驗證碼)
你沒有看錯,全自動驗證~~~
黑科技?還是黑程式碼?
我感覺這個看在你用啥,對不對?反正我用來(* * * * ) 你懂得
好了,先說一下用到的東西
- selenium (本意是用來全自動測試)
- Phantomjs (一種沒有介面的瀏覽器)
- ** 驗證碼識別器(一塊錢可用100次的這種)
關門放程式碼
from selenium import webdriver from PIL import Image if __name__ == '__main__': wbe = webdriver.PhantomJS() wbe.get("https://www.某個網站的登入頁面.com/login/index.html")//你可以拿知乎,百度,等等測試 element = wbe.find_element_by_xpath('//*[@id="entry_name"]/p[3]/img')//驗證碼所在的xpath路徑 left = element.location['x'] top = element.location['y'] right = element.location['x'] + element.size['width'] bottom = element.location['y'] + element.size['height'] im = Image.open(r'登入頁.png')//全頁面截圖 im = im.crop((left,top,right,bottom)) im.save('驗證碼.png')
#!/usr/bin/env python # coding:utf-8 import requests from hashlib import md5 class RClient(object): def __init__(self,username,password,soft_id,soft_key): self.username = username self.password = md5(password).hexdigest() self.soft_id = soft_id self.soft_key = soft_key self.base_params = { 'username': self.username,'password': self.password,'softid': self.soft_id,'softkey': self.soft_key,} self.headers = { 'Connection': 'Keep-Alive','Expect': '100-continue','User-Agent': 'ben',} def rk_create(self,im,im_type,timeout=60): """ im: 圖片位元組 im_type: 題目型別 """ params = { 'typeid': im_type,'timeout': timeout,} params.update(self.base_params) files = {'image': ('a.png',im)} r = requests.post('http://api.ruokuai.com/create.json',data=params,files=files,headers=self.headers) return r.json() def rk_report_error(self,im_id): """ im_id:報錯題目的ID """ params = { 'id': im_id,} params.update(self.base_params) r = requests.post('http://api.ruokuai.com/reporterror.json',headers=self.headers) return r.json() def get_code(): rc = RClient('使用者名稱','密碼','94522','62c235939b7240879453f31603733fd6')//想拿下測試的留言我,教你拿到測試賬號 im = open('a.png','rb').read() print rc.rk_create(im,3040)
完整程式碼
#!/usr/bin/env python # coding:utf-8 from selenium import webdriver from PIL import Image import requests from hashlib import md5 import time class RClient(object): def __init__(self,soft_key): self.username = username self.password = md5(password.encode("utf-8")).hexdigest() self.soft_id = soft_id self.soft_key = soft_key self.base_params = { 'username': self.username,headers=self.headers) return r.json() def get_code(im_file): rc = RClient('賬號','62c235939b7240879453f31603733fd6') im_source = open(im_file,"rb").read() print(rc.rk_create(im_source,3040)) if __name__ == '__main__': wbe = webdriver.PhantomJS() wbe.get("https://www.dajiang365.com/login/index.html") time.sleep(2) wbe.save_screenshot("das.png") element = wbe.find_element_by_xpath('//*[@id="entry_name"]/p[3]/img') left = element.location['x'] top = element.location['y'] right = element.location['x'] + element.size['width'] bottom = element.location['y'] + element.size['height'] im = Image.open(r'das.png') im = im.crop((left,bottom)) im.save('a.png') time.sleep(2) get_code("a.png")
總結
到此這篇關於python圖片驗證碼識別最新模組muggle_ocr的示例程式碼的文章就介紹到這了,更多相關python 驗證碼識別模組muggle_ocr內容請搜尋我們以前的文章或繼續瀏覽下面的相關文章希望大家以後多多支援我們!