自学教程：Python基于百度AI实现抓取表情包

# 抓取百度贴吧某个帖子里的所有图片import requestsimport timeimport threadingimport queuefrom bs4 import BeautifulSoupimport chardetimport ostiezi_url = "https://tieba.baidu.com/p/5522091060"headers = {    'Host': 'tieba.baidu.com',    'User-Agent': 'User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KH'                  'TML, like Gecko) Chrome/90.0.4430.212 Safari/537.36',}pic_save_dir = 'tiezi_pic/'if not os.path.exists(pic_save_dir):  # 判断文件夹是否存在，不存在就创建    os.makedirs(pic_save_dir)pic_urls_file = 'tiezi_pic_urls.txt'download_q = queue.Queue()  # 下载队列# 获得页数def get_page_count():    try:        resp = requests.get(tiezi_url, headers=headers, timeout=5)        if resp is not None:            resp.encoding = chardet.detect(resp.content)['encoding']            html = resp.text            soup = BeautifulSoup(html, 'lxml')            a_s = soup.find("ul", attrs={'class': 'l_posts_num'}).findAll("a")            for a in a_s:                if a.get_text() == '尾页':                    return a['href'].split('=')[1]    except Exception as e:        print(str(e))# 下载线程class PicSpider(threading.Thread):    def __init__(self, t_name, func):        self.func = func        threading.Thread.__init__(self, name=t_name)    def run(self):        self.func()# 获得每页里的所有图片URLdef get_pics(count):    params = {        'pn': count,        'ajax': '1',        't': int(time.time())    }    try:        resp = requests.get(tiezi_url, headers=headers, timeout=5, params=params)        if resp is not None:            resp.encoding = chardet.detect(resp.content)['encoding']            html = resp.text            soup = BeautifulSoup(html, 'lxml')            imgs = soup.findAll('img', attrs={'class': 'BDE_Image'})            for img in imgs:                print(img['src'])                with open(pic_urls_file, 'a') as fout:                    fout.write(img['src'])                    fout.write('/n')            return None    except Exception:        pass# 下载线程调用的方法def down_pics():    global download_q    while not download_q.empty():        data = download_q.get()        download_pic(data)        download_q.task_done()# 下载调用的方法def download_pic(img_url):    try:        resp = requests.get(img_url, headers=headers, timeout=10)        if resp.status_code == 200:            print("下载图片:" + img_url)            pic_name = img_url.split("/")[-1][0:-1]            with open(pic_save_dir + pic_name, "wb+") as f:                f.write(resp.content)    except Exception as e:        print(e)if __name__ == '__main__':    print("检索判断链接文件是否存在：")    if not os.path.exists(pic_urls_file):        print("不存在，开始解析帖子...")        page_count = get_page_count()        if page_count is not None:            headers['X-Requested-With'] = 'XMLHttpRequest'            for page in range(1, int(page_count) + 1):                get_pics(page)        print("链接已解析完毕！")        headers.pop('X-Requested-With')    else:        print("存在")    print("开始下载图片~~~~")    headers['Host'] = 'imgsa.baidu.com'    fo = open(pic_urls_file, "r")    pic_list = fo.readlines()    threads = []    for pic in pic_list:        download_q.put(pic)    for i in range(0, len(pic_list)):        t = PicSpider(t_name='线程' + str(i), func=down_pics)        t.daemon = True        t.start()        threads.append(t)    download_q.join()    for t in threads:        t.join()    print("图片下载完毕")

pip install baidu-aip 

from aip import AipOcr# 新建一个AipOcr对象config = {    'appId': '填写自己的appId',    'apiKey': '填写自己的apiKey',    'secretKey': '填写自己的secretKey'}client = AipOcr(**config)# 识别图片里的文字def img_to_str(image_path):    # 读取图片    with open(image_path, 'rb') as fp:        image = fp.read()        # 调用通用文字识别, 图片参数为本地图片    result = client.basicGeneral(image)    # 返回拼接结果    if 'words_result' in result:        return '/n'.join([w['words'] for w in result['words_result']])if __name__ == '__main__':    print(img_to_str('tiezi_pic/5c0ddb1e4134970aebd593e29ecad1c8a5865dbd.jpg'))

{'words_result': [{'words': 'o。o'}, {'words': '6226-16:59'}, {'words': '绝望jpg'}], 'log_id': 1393611954748129280, 'words_result_num': 3}o。o6226-16:59绝望jpg

# 识别图片文字，批量命名图片文字import osfrom aip import AipOcrimport reimport datetime# 新建一个AipOcr对象config = {    'appId': '填写自己的appId',    'apiKey': '填写自己的apiKey',    'secretKey': '填写自己的secretKey'}client = AipOcr(**config)pic_dir = r"tiezi_pic/"# 读取图片def get_file_content(file_path):    with open(file_path, 'rb') as fp:        return fp.read()# 识别图片里的文字def img_to_str(image_path):    image = get_file_content(image_path)    # 调用通用文字识别, 图片参数为本地图片    result = client.basicGeneral(image)    # 结果拼接返回    words_list = []    if 'words_result' in result:        if len(result['words_result']) > 0:            for w in result['words_result']:                words_list.append(w['words'])            file_name = get_longest_str(words_list)            print(file_name)            file_dir_name = pic_dir + str(file_name).replace("/", "") + '.jpg'            if os.path.exists(file_dir_name):  # 处理文件重名问题                sec = datetime.datetime.now().microsecond  # 获取当前毫秒时值                file_dir_name = pic_dir + str(file_name).replace("/", "") + str(sec) + '.jpg'            try:                os.rename(image_path, file_dir_name)            except Exception:                print(" 重命名失败：", image_path, " => ", file_name)# 获取字符串列表中最长的字符串def get_longest_str(str_list):    pat = re.compile(r'[/u4e00-/u9fa5A-Za-z]+')    str = max(str_list, key=hanzi_len)    result = pat.findall(str)    return ''.join(result)def hanzi_len(item):    pat = re.compile(r'[/u4e00-/u9fa5]+')    sum = 0    for i in item:        if pat.search(i):            sum += 1    return sum# 遍历某个文件夹下所有图片def query_picture(dir_path):    pic_path_list = []    for filename in os.listdir(dir_path):        pic_path_list.append(dir_path + filename)    return pic_path_listif __name__ == '__main__':    pic_list = query_picture(pic_dir)    if len(pic_list) > 0:        for i in pic_list:            img_to_str(i)