環(huán)境搭建

基于linux/mac、Python

1.安裝Python圖像庫(kù)

    pip install Pillow

2.安裝Python庫(kù)Pytesseract

    pip install pytesseract

3.安裝Python庫(kù)tesseract

    pip install tesseract

4.安裝leptonica

下載地址：http://www.leptonica.com/download.html

    ./configure
    make
    make install

5.安裝tesseract-ocr

下載地址：https://github.com/tesseract-ocr/tesseract

    ./autogen.sh
    CPPFLAGS="-I/usr/local/include" LDFLAGS="-L/usr/local/lib" ./configure
    make
    make install

安裝完成后，再下載tessdata，將其放置于tessdata目錄。

Python腳本：

#!/usr/bin/env python
#-*- coding:utf-8 -*-
# author:wdl 
# time:2017-03-08 pm

import os
import sys
import time
import requests
from PIL import Image
import pytesseract
import subprocess

code_url = "https://www.jiguang.cn/captcha/login/"

def identification_code(url):

    #獲取驗(yàn)證碼并保存
    with open("captcha.jpg","wb") as i:
        i.write(requests.get(url,stream=True).content)

    #打開圖片
    im = Image.open("captcha.jpg")

    #轉(zhuǎn)化圖片為灰度圖
    im = im.convert('L')

    def initTable(threshold=140):
        table = []
        for i in range(256):
            if i < threshold:
                table.append(0)
            else:
                table.append(1)
        return table

    #灰度圖二值化
    bininaryImage = im.point(initTable(),'1')

    #將圖片轉(zhuǎn)化為文本
    return pytesseract.image_to_string(bininaryImage,lang="eng",config="-psm 7")

print(identification_code(code_url))