yd/ex02(1).py

import ddddocr
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.edge.options import Options
from selenium.webdriver.edge.service import Service as EdgeService
import re
import time



def getWeb():
    
    global edge

    edge_options = Options()
    edge_options.add_experimental_option("excludeSwitches", ["enable-logging'"])
    edge_options.add_experimental_option("excludeSwitches", ["enable-automation"]) 
    edge_options.add_experimental_option('useAutomationExtension', False) 
    #edge_options.add_argument('headless')
    service = EdgeService(executable_path=r'D:\222\msedgedriver.exe')
    edge = webdriver.Edge(service=service, options=edge_options)
    edge.execute_cdp_cmd("Page.addScriptToEvaluateOnNewDocument", {"source": 
          """
            Object.defineProperty(navigator, 'webdriver', {
              get: () => undefined
            })
          """
    })
    

def getSoGou_link(WX_ID):

    url = f'https://weixin.sogou.com/weixin?type=1&s_from=input&query={WX_ID}'
    edge.get(url)
    print(">>> 开始识别验证码")

    while True:
        try:
            edge.find_element(By.CSS_SELECTOR ,' #seccodeImage').screenshot('tempVerification_code.png')
        except:
            break
        ocr = ddddocr.DdddOcr(show_ad=False)
        with open('tempVerification_code.png', 'rb') as f:
            img_bytes = f.read()
        Verification_code = (ocr.classification(img_bytes)).upper()
        print('>>> 识别成功!')
        print(Verification_code)
        edge.find_element(By.NAME, 'c').send_keys(Verification_code)
        time.sleep(0.5)
        edge.find_element(By.ID, 'submit').click()
        time.sleep(1)
        try:
            edge.find_element(By.ID, 'change-img').click()
            time.sleep(0.5)
        except:
            break

    WX_link_list = edge.find_elements(By.XPATH, '//*[@id="sogou_vr_11002301_box_0"]/dl/dd/a')
    
    if len(WX_link_list) == 0 :
        return False

    return WX_link_list[0].get_attribute('href')


def getWX_html(link):

    edge.get(link)
    time.sleep(3)
    try:
        txt = edge.find_element(By.XPATH, '//*[@id="img-content"]').text
        print(txt.split('\n'))
    except:
        pass

    try:
        img_list = edge.find_elements(By.TAG_NAME, 'img')
        for i in img_list:
            if i.get_attribute('data-src') != None:
                print(i.get_attribute('data-src'))
    except:
        pass
    
    try:
        video_list = edge.find_elements(By.TAG_NAME, 'video')
        for i in video_list:
            print(i.get_attribute('src'))
    except:
        pass
    
    


if __name__ == "__main__":

    with open('id.txt', 'r', encoding='UTF-8') as file:
        id_data = file.read()
        id = re.compile(r'\'query\' \=\> \'(.*)\'').findall(id_data)

    getWeb()
    for x in id:
        print('--'*60)
        link = getSoGou_link(WX_ID=x)
        if link == False:
            print(">>> Error：没有文章")
            continue
        print(link)
        getWX_html(link=link)