关于使用mac搭建tesseract-ocr的血泪总结

1.使用pyhton安装pytesseract

2.使用brew 安装tesseract

3.将pytesseract包的里的pytesseract.py 中的

tesseract_cmd的路径换成brew 安装的tesseract包的安装目录。

这样才能一次性成功。 

 完整源码

import pytesseract
from PIL import Image
import pymysql
from coverage.annotate import os

# 建立数据库连接
conn = pymysql.connect(
    host='localhost',
    port=3306,
    user='root',
    password='root',
    db='cut_movie',
    charset='utf8'
)

# 获取游标
cursor = conn.cursor()

# 执行sql语句
sql = 'select * from frame'
rows = cursor.execute(sql)  # 返回结果是受影响的行数
data = cursor.fetchall()
for row in data:
    id = row[0]
    va = row[1] + ""
    # va = va.replace("/Users/zhangjunhua/Movies/young/vedio/", "/Users/zhangjunhua/Movies/young/cut_video/")
    if not os.path.exists(va):
        print("文件不存在")
        continue
    data = Image.open(va)

    res = pytesseract.image_to_string(data, lang='chi_sim')
    print(res)
    if not res:
        res = "无"
    else:
        res = ','.join(res[0])
    print(res)
    if res != '' or res != '无':
        sta = 0
    else:
        sta = 1
    sql1 = 'UPDATE frame SET va="%s",status=%s WHERE id=%s'
    val = (res,sta,id)
    cursor.execute(sql1,val)
    conn.commit()
# 关闭游标
cursor.close()

# 关闭连接
conn.close()