pyocr测试

import requests
import shutil
import os


from PIL import Image
import sys

import pyocr
import pyocr.builders

tools = pyocr.get_available_tools()
if len(tools) == 0:
    print("No OCR tool found")
    sys.exit(1)
# The tools are returned in the recommended order of usage
tool = tools[0]

langs = tool.get_available_languages()
print("Available languages: %s" % ", ".join(langs))
lang = langs[0]

total = 10000
count = 0
headers = {}
f = open('headers.txt', 'r')
for line in f:
    if ':' in line:
        i = line.index(':')
        k = line[:i]
        v = line[i + 1:]
        k = k.strip()
        v = v.strip()
        headers[k] = v

try:
    os.mkdir('code')
except:
    pass
path_tmp = os.path.join('code', '{}.jpeg')
for i in range(total):
    path = path_tmp.format(i)
    r = requests.get('https://plogin.m.jd.com/cgi-bin/m/authcode?mod=login',
                     headers=headers,
                     stream=True)
    if r.status_code != 200:
        continue
    with open(path, 'wb') as f:
        r.raw.decode_content = True
        shutil.copyfileobj(r.raw, f)
    txt = tool.image_to_string(
        Image.open(path), lang=lang,
        builder=pyocr.builders.TextBuilder()
    )
    print(txt, len(txt))
    if len(txt) == 4:
        count += 1


print("{}%% can ocr".format(float(count) / total))