import re
from urllib.parse import urljoin

import requests
from bs4 import BeautifulSoup
import pytesseract
from PIL import Image

cookies = {
    'session': '.eJyrViotTi1SsqpWyiyOT0zJzcxTsjLQUcrJTwexSopKU3WUcvOTMnNSlayUDM3gQEkHrDE-M0XJyhjCzkvMBSmKKTVNMjMDkiamFkq1tQDfeR3n.YLOC4w.Xbnx1QbrvUh8OUPb5jauC_Aau9U',
}

headers = {
    'Connection': 'keep-alive',
    'Pragma': 'no-cache',
    'Cache-Control': 'no-cache',
    'Upgrade-Insecure-Requests': '1',
    'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_16_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.92 Safari/537.36',
    'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,image/apng,*/*;q=0.8,application/signed-exchange;v=b3;q=0.9',
    'Accept-Language': 'zh-CN,zh;q=0.9,en;q=0.8',
}

root_url = 'http://47.103.13.124:8001/'

url = urljoin(root_url, 'phone_picture')

response = requests.get(url, headers=headers, cookies=cookies, verify=False)

soup = BeautifulSoup(response.text, 'lxml')
imgs = soup.find('tbody').find_all('img')

urls = [img.attrs.get('src') for img in imgs]

for url in urls:
    # 获得完整的url
    url = urljoin(root_url, url)
    img = requests.get(url, stream=True).raw
    img = Image.open(img)
    res = pytesseract.image_to_string(img)
    phone_number = re.match('\d*', res).group()
    print(f'URL: {url}, OCR Result: {res}, PhoneNumber: {phone_number}')