python用提取截图信息来实现采集某某买菜数据，干货太多，百分百原创，仅供学习与研究，【强烈建议收藏】

序言

android手机可以实现滚动截图，然后用要采集某某买菜的产品数据，主要是分析产品数据来选择精品商品，方便选品。

可以先用android手机支持滚动截图，再用神奇图片分割软件把截图分割成各个小份，再用图片识别技术读取图片上的文字，再把截图和文字通过接口传到云端。

原创代码如下：

# -*- coding: utf-8 -*-
import os
import pytesseract
from PIL import Image

from base.base_api import BaseApi
from base.base_root import BaseRoot
from base.req_up_data import up_file

curpath = BaseRoot.root_path
curpath=curpath.replace("\\",'/')
folder = "import"
pic_dir = curpath + f'{folder}/'




def traverse_dir(path):
    for root, dirs, files in os.walk(path):
        if "0000" in root and "finish" not in root:
            src_path= f"{root}"
            desc_path= f"{root}_finish"

            #os.rename(src_path,desc_path)

            for file in files:
                if "jpg" in file:
                    mydict = {}
                    file_arr = file.split("-")


                    mydict['warehouse_son_name'] = file_arr[0]
                    mydict['warehouse_son_code'] = file_arr[1]
                    mydict['warehouse_name'] = file_arr[2]
                    mydict['warehouse_code'] = file_arr[3]
                    mydict['category'] = file_arr[4]
                    mydict['near_buy'] =''
                    mydict['day_buy'] =''
                    mydict['year'] = file_arr[5]
                    mydict['month'] = file_arr[6]
                    mydict['day'] = file_arr[7][:2]
                    mydict['goods_name'] = ""
                    mydict['goods_price'] ="0"

                    mydict['now_day'] = f"{mydict['year']}-{mydict['month']}-{mydict['day']}"

                    #print(file_arr)
                    resolve_pic = f"{root}/{file}"
                    #print(resolve_pic)
                    file_type = resolve_pic.split('.')[-1]
                    #print(file_type)

                    save_file_url = up_file(resolve_pic, file_type)
                    #print(save_file_url)

                    mydict['img_url'] = f"https://你的oss地址.aliyuncs.com{save_file_url}"


                    image = Image.open(resolve_pic)
                    content = pytesseract.image_to_string(image, lang='chi_sim+eng')
                    content = str(content).split("\n")
                    #print(content)
                    save_content = ""
                    for temp_content in content:

                        if "附近" in temp_content:
                            mydict['near_buy']=temp_content
                        elif "无理由退换" in temp_content:
                           pass
                        elif "贝勾" in temp_content:
                           pass
                        elif "优晨价" in temp_content:
                            mydict['goods_price'] = "0.1"

                        else:
                            save_content = save_content + temp_content

                    mydict['goods_name'] = save_content.replace(' ','')

                    print(mydict)
                    response_text = BaseApi.uploadGoodsData(mydict)
                    print(f"------打印第{resolve_pic}提交返回开始------")
                    print(response_text)
                    print(f"------打印第{resolve_pic}提交返回结束------")

            os.rename(src_path,desc_path)
            #print("当前目录：", root)
            #print("子目录列表：", dirs)
            #print("文件列表：", files)



dir_path = pic_dir
#print('待遍历的目录为：', dir_path)
#print('遍历结果为：')
traverse_dir(dir_path)