UnicodeDecodeError: 'utf-8' codec can't decode byte 0xd5 in position 24: invalid continuation byte

# -*- coding: utf-8 -*-

# website: http://30daydo.com

# @Time : 2019/2/23 19:34

# @File : youdao.py

# 解密有道词典的JS





import hashlib

import random

import requests

import time





def md5_(word):

    s = bytes(word, encoding='utf8')

    m = hashlib.md5()

    m.update(s)

    ret = m.hexdigest()

    return ret



def get_sign(word, salt):

    ret = md5_('fanyideskweb' + word + salt + 'p09@Bn{h02_BIEe]$P^nG')

    return ret





def youdao(word):

    url = 'http://fanyi.youdao.com/translate_o?smartresult=dict&smartresult=rule'

    headers = {

        'Host': 'fanyi.youdao.com',

        'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:47.0) Gecko/20100101 Firefox/47.0',

        'Accept': 'application/json, text/javascript, */*; q=0.01',

        'Accept-Language': 'zh-CN,zh;q=0.8,en-US;q=0.5,en;q=0.3',

        'Accept-Encoding': 'gzip, deflate',

        'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8',

        'X-Requested-With': 'XMLHttpRequest',

        'Referer': 'http://fanyi.youdao.com/',

        'Content-Length': '252',

        'Cookie': 'YOUDAO_MOBILE_ACCESS_TYPE=1; OUTFOX_SEARCH_USER_ID=1672542763@10.169.0.83; JSESSIONID=aaaWzxpjeDu1gbhopLzKw; ___rl__test__cookies=1550913722828; OUTFOX_SEARCH_USER_ID_NCOO=372126049.6326876',

        'Connection': 'keep-alive',

        'Pragma': 'no-cache',

        'Cache-Control': 'no-cache',

    }



    ts = str(int(time.time()*1000))

    salt=ts+str(random.randint(0,10))

    bv = md5_("5.0 (Windows)")

    sign= get_sign(word,salt)



    post_data = {

        'i': word,

        'from': 'AUTO', 'to': 'AUTO', 'smartresult': 'dict', 'client': 'fanyideskweb', 'salt': salt,

        'sign': sign, 'ts': ts, 'bv': bv, 'doctype': 'json', 'version': '2.1',

        'keyfrom': 'fanyi.web', 'action': 'FY_BY_REALTIME', 'typoResult': 'false'

    }



    r = requests.post(

        url=url,

        headers=headers,

        data=post_data

    )



    for item in r.json().get('smartResult',{}).get('entries'):

        print(item)



word='student'

youdao(word)

from PIL import Image

im = Image.open('chinese.jpg')

plt.figure(figsize=(20,20))

plt.imshow(im)



pytesseract.image_to_string(im,lang='chi_sim')

'可L又使用以下的语句i上图片显示大 此'

""" 读取图片 """

def get_file_content(filePath):

    with open(filePath, 'rb') as fp:

        return fp.read()



image = get_file_content('example.jpg')



""" 调用通用文字识别, 图片参数为本地图片 """

client.basicGeneral(image);



""" 如果有可选参数 """

options = {}

options["language_type"] = "CHN_ENG"

options["detect_direction"] = "true"

options["detect_language"] = "true"

options["probability"] = "true"



from aip import AipOcr



""" 你的 APPID AK SK """

APP_ID = '你的 App ID'

API_KEY = '你的 Api Key'

SECRET_KEY = '你的 Secret Key'



client = AipOcr(APP_ID, API_KEY, SECRET_KEY)





""" 带参数调用通用文字识别, 图片参数为本地图片 """

client.basicGeneral(image, options)



url = "https//www.x.com/sample.jpg"



""" 调用通用文字识别, 图片参数为远程url图片 """

client.basicGeneralUrl(url);



""" 如果有可选参数 """

options = {}

options["language_type"] = "CHN_ENG"

options["detect_direction"] = "true"

options["detect_language"] = "true"

options["probability"] = "true"



""" 带参数调用通用文字识别, 图片参数为远程url图片 """

client.basicGeneralUrl(url, options)

可以使用以下的语句让图片显示大些

im = Image.open('chinese.png')

plt.figure(figsize=(20,20))

plt.imshow(im)

from  setting import get_mysql_conn,get_engine

import pandas as pd

import pymongo

from pyecharts import Geo,Style,Map

engine = get_engine('db_stock',local='local')

# 堆叠图

from pyecharts import Bar

df = pd.read_sql('tb_bond_jisilu',con=engine)



result ={}

for name,grades in df.groupby('评级'):

#     print(name,grades[['可转债名称','可转债价格']])

    for each in grades['可转债价格']:

        result.setdefault(name,)

        result[name].append(each)

        

        

# 确定价格的范围



value = [str(i) for i in range(85,140)]

ret = [0]*len(value)

ret1 = dict(zip(value,ret))



ret_A_add = ret1.copy()

for item in result['A+']:

    for k in ret1:

        if float(k)+0.5>item and float(k)-0.5<=item:

            ret_A_add[k]+=1

            

retAA_ = ret1.copy()

for item in result['']:

    for k in ret1:

        if float(k)+0.5>item and float(k)-0.5<=item:

            retAA_[k]+=1



retAA = ret1.copy()

for item in result['AA']:

    for k in ret1:

        if float(k)+0.5>item and float(k)-0.5<=item:

            retAA[k]+=1

            

retAA_add = ret1.copy()

for item in result['AA+']:

    for k in ret1:

        if float(k)+0.5>item and float(k)-0.5<=item:

            retAA_add[k]+=1

            

retAAA = ret1.copy()

for item in result['AAA']:

    for k in ret1:

        if float(k)+0.5>item and float(k)-0.5<=item:

            retAAA[k]+=1



bar = Bar('可转债价格分布')

bar.add('A+',value,list(ret_A_add.values()),is_stack=True,yaxis_max=11)

bar.add('',value,list(retAA_.values()),is_stack=True,yaxis_max=11)

bar.add('AA',value,list(retAA.values()),is_stack=True,yaxis_max=11)

bar.add('AA+',value,list(retAA_add.values()),is_stack=True,yaxis_max=11)

bar.add('AAA',value,list(retAAA.values()),is_stack=True,yaxis_max=11)