{"id":1149908,"date":"2025-01-13T16:55:22","date_gmt":"2025-01-13T08:55:22","guid":{"rendered":"https:\/\/docs.pingcode.com\/ask\/ask-ask\/1149908.html"},"modified":"2025-01-13T16:55:24","modified_gmt":"2025-01-13T08:55:24","slug":"python%e8%a7%86%e9%a2%91%e5%a6%82%e4%bd%95%e6%8d%a2%e4%ba%ba%e8%84%b8","status":"publish","type":"post","link":"https:\/\/docs.pingcode.com\/ask\/1149908.html","title":{"rendered":"python\u89c6\u9891\u5982\u4f55\u6362\u4eba\u8138"},"content":{"rendered":"

\"python\u89c6\u9891\u5982\u4f55\u6362\u4eba\u8138\"<\/p>\n

\u5728Python\u4e2d\u5b9e\u73b0\u89c6\u9891\u6362\u8138\u6280\u672f\uff0c\u901a\u5e38\u9700\u8981\u4f7f\u7528\u4e00\u4e9b\u8ba1\u7b97\u673a\u89c6\u89c9\u5e93\u548c\u6df1\u5ea6\u5b66\u4e60\u6846\u67b6\u3002\u4e3b\u8981\u6b65\u9aa4\u5305\u62ec\uff1a\u4eba\u8138\u68c0\u6d4b\u3001\u4eba\u8138\u5bf9\u9f50\u3001\u8138\u90e8\u7279\u5f81\u63d0\u53d6\u3001\u8138\u90e8\u7279\u5f81\u66ff\u6362\u3001\u751f\u6210\u65b0\u8138\u90e8\u56fe\u50cf\u3001\u5c06\u65b0\u8138\u90e8\u56fe\u50cf\u5408\u6210\u5230\u89c6\u9891\u5e27\u4e2d<\/strong>\u3002\u5176\u4e2d\uff0c\u4eba\u8138\u68c0\u6d4b<\/strong>\u662f\u6700\u5173\u952e\u7684\u6b65\u9aa4\u4e4b\u4e00\uff0c\u4e0b\u9762\u8be6\u7ec6\u4ecb\u7ecd\u3002<\/p>\n<\/p>\n

\u4eba\u8138\u68c0\u6d4b<\/strong>\u662f\u6362\u8138\u6280\u672f\u7684\u57fa\u7840\uff0c\u5b83\u7684\u51c6\u786e\u6027\u76f4\u63a5\u5f71\u54cd\u5230\u540e\u7eed\u6b65\u9aa4\u7684\u6548\u679c\u3002\u4eba\u8138\u68c0\u6d4b\u5e38\u7528\u7684\u5de5\u5177\u5305\u62ecOpenCV\u3001dlib\u548cMTCNN\u7b49\u3002dlib\u5e93\u4e2d\u7684HOG\uff08Histogram of Oriented Gradients\uff09\u548cCNN\uff08Convolutional Neural Network\uff09\u6a21\u578b\u662f\u68c0\u6d4b\u4eba\u8138\u7684\u5e38\u7528\u65b9\u6cd5\u3002<\/p>\n<\/p>\n

\u63a5\u4e0b\u6765\uff0c\u6211\u4eec\u5c06\u5206\u6b65\u9aa4\u8be6\u7ec6\u4ecb\u7ecd\u5982\u4f55\u5728Python\u4e2d\u5b9e\u73b0\u89c6\u9891\u6362\u8138\u6280\u672f\u3002<\/p>\n<\/p>\n

\u4e00\u3001\u51c6\u5907\u73af\u5883<\/h2>\n<\/p>\n

\u8981\u5728Python\u4e2d\u8fdb\u884c\u89c6\u9891\u6362\u8138\uff0c\u4f60\u9700\u8981\u5b89\u88c5\u4e00\u4e9b\u5fc5\u8981\u7684\u5e93\uff0c\u5305\u62ecOpenCV\u3001dlib\u548cnumpy\u3002\u4f60\u53ef\u4ee5\u4f7f\u7528pip\u5b89\u88c5\u8fd9\u4e9b\u5e93\uff1a<\/p>\n<\/p>\n

pip install opencv-python dlib numpy<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e8c\u3001\u52a0\u8f7d\u89c6\u9891\u548c\u68c0\u6d4b\u4eba\u8138<\/h2>\n<\/p>\n
\u9996\u5148\uff0c\u4f7f\u7528OpenCV\u52a0\u8f7d\u89c6\u9891\uff0c\u5e76\u9010\u5e27\u68c0\u6d4b\u4eba\u8138\u3002\u4e0b\u9762\u662f\u4e00\u4e2a\u7b80\u5355\u7684\u4ee3\u7801\u793a\u4f8b\uff1a<\/p>\n<\/p>\n
import cv2<\/p>\n
import dlib<\/p>\n
\u52a0\u8f7d\u89c6\u9891<\/strong><\/h2>\n
video_path = 'input_video.mp4'<\/p>\n
cap = cv2.VideoCapture(video_path)<\/p>\n
\u52a0\u8f7ddlib\u7684\u4eba\u8138\u68c0\u6d4b\u5668<\/strong><\/h2>\n
detector = dlib.get_frontal_face_detector()<\/p>\n
while cap.isOpened():<\/p>\n
    ret, frame = cap.read()<\/p>\n
    if not ret:<\/p>\n
        break<\/p>\n
    # \u8f6c\u6362\u4e3a\u7070\u5ea6\u56fe\u50cf<\/p>\n
    gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)<\/p>\n
    # \u68c0\u6d4b\u4eba\u8138<\/p>\n
    faces = detector(gray)<\/p>\n
    for face in faces:<\/p>\n
        x, y, w, h = (face.left(), face.top(), face.width(), face.height())<\/p>\n
        cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 255, 0), 2)<\/p>\n
    cv2.imshow('Video', frame)<\/p>\n
    if cv2.wAI<\/a>tKey(1) & 0xFF == ord('q'):<\/p>\n
        break<\/p>\n
cap.release()<\/p>\n
cv2.destroyAllWindows()<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e09\u3001\u4eba\u8138\u5bf9\u9f50<\/h2>\n<\/p>\n
\u68c0\u6d4b\u5230\u4eba\u8138\u540e\uff0c\u9700\u8981\u5bf9\u5176\u8fdb\u884c\u5bf9\u9f50\uff0c\u4ee5\u4fbf\u540e\u7eed\u7684\u7279\u5f81\u63d0\u53d6\u548c\u66ff\u6362\u66f4\u52a0\u51c6\u786e\u3002dlib\u5e93\u63d0\u4f9b\u4e8668\u4e2a\u9762\u90e8\u5173\u952e\u70b9\u68c0\u6d4b\u5668\uff0c\u53ef\u4ee5\u5e2e\u52a9\u6211\u4eec\u5bf9\u9f50\u4eba\u8138\u3002\u4e0b\u9762\u662f\u4ee3\u7801\u793a\u4f8b\uff1a<\/p>\n<\/p>\n
import dlib<\/p>\n
\u52a0\u8f7ddlib\u768468\u4e2a\u9762\u90e8\u5173\u952e\u70b9\u68c0\u6d4b\u6a21\u578b<\/strong><\/h2>\n
predictor_path = 'shape_predictor_68_face_landmarks.dat'<\/p>\n
predictor = dlib.shape_predictor(predictor_path)<\/p>\n
def get_landmarks(image, face):<\/p>\n
    landmarks = predictor(image, face)<\/p>\n
    return [(point.x, point.y) for point in landmarks.parts()]<\/p>\n
\u5728\u4eba\u8138\u68c0\u6d4b\u90e8\u5206\u7684\u4ee3\u7801\u4e2d\uff0c\u6dfb\u52a0\u4ee5\u4e0b\u5185\u5bb9<\/strong><\/h2>\n
for face in faces:<\/p>\n
    landmarks = get_landmarks(gray, face)<\/p>\n
    for (x, y) in landmarks:<\/p>\n
        cv2.circle(frame, (x, y), 2, (0, 0, 255), -1)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u56db\u3001\u8138\u90e8\u7279\u5f81\u63d0\u53d6\u4e0e\u66ff\u6362<\/h2>\n<\/p>\n
\u63a5\u4e0b\u6765\uff0c\u9700\u8981\u63d0\u53d6\u6e90\u8138\u548c\u76ee\u6807\u8138\u7684\u7279\u5f81\uff0c\u5e76\u8fdb\u884c\u66ff\u6362\u3002\u6211\u4eec\u53ef\u4ee5\u4f7f\u7528OpenCV\u7684\u4eff\u5c04\u53d8\u6362\u6765\u5b9e\u73b0\u8fd9\u4e00\u70b9\u3002<\/p>\n<\/p>\n
import numpy as np<\/p>\n
def apply_affine_transform(src, src_tri, dst_tri, size):<\/p>\n
    warp_mat = cv2.getAffineTransform(np.float32(src_tri), np.float32(dst_tri))<\/p>\n
    dst = cv2.warpAffine(src, warp_mat, (size[0], size[1]), None, flags=cv2.INTER_LINEAR, borderMode=cv2.BORDER_REFLECT_101)<\/p>\n
    return dst<\/p>\n
def warp_triangle(img1, img2, t1, t2):<\/p>\n
    # \u83b7\u53d6\u5305\u56f4\u4e09\u89d2\u5f62\u7684\u8fb9\u754c\u6846<\/p>\n
    r1 = cv2.boundingRect(np.float32([t1]))<\/p>\n
    r2 = cv2.boundingRect(np.float32([t2]))<\/p>\n
    # \u504f\u79fb\u4e09\u89d2\u5f62\u5230(0, 0)\u70b9<\/p>\n
    t1_rect = []<\/p>\n
    t2_rect = []<\/p>\n
    for i in range(0, 3):<\/p>\n
        t1_rect.append(((t1[i][0] - r1[0]), (t1[i][1] - r1[1])))<\/p>\n
        t2_rect.append(((t2[i][0] - r2[0]), (t2[i][1] - r2[1])))<\/p>\n
    # \u83b7\u53d6\u63a9\u7801<\/p>\n
    mask = np.zeros((r2[3], r2[2], 3), dtype=np.float32)<\/p>\n
    cv2.fillConvexPoly(mask, np.int32(t2_rect), (1.0, 1.0, 1.0), 16, 0)<\/p>\n
    # \u5e94\u7528\u4eff\u5c04\u53d8\u6362<\/p>\n
    img1_rect = img1[r1[1]:r1[1] + r1[3], r1[0]:r1[0] + r1[2]]<\/p>\n
    size = (r2[2], r2[3])<\/p>\n
    img2_rect = apply_affine_transform(img1_rect, t1_rect, t2_rect, size)<\/p>\n
    # \u5c06\u56fe\u50cf\u5408\u6210\u5230\u76ee\u6807\u56fe\u50cf<\/p>\n
    img2_rect = img2_rect * mask<\/p>\n
    img2[r2[1]:r2[1] + r2[3], r2[0]:r2[0] + r2[2]] = img2[r2[1]:r2[1] + r2[3], r2[0]:r2[0] + r2[2]] * (1 - mask)<\/p>\n
    img2[r2[1]:r2[1] + r2[3], r2[0]:r2[0] + r2[2]] = img2[r2[1]:r2[1] + r2[3], r2[0]:r2[0] + r2[2]] + img2_rect<\/p>\n
\u66ff\u6362\u8138\u90e8\u7279\u5f81<\/strong><\/h2>\n
\u5047\u8bbesrc_points\u548cdst_points\u662f\u6e90\u8138\u548c\u76ee\u6807\u8138\u7684\u5173\u952e\u70b9<\/strong><\/h2>\n
for i in range(len(triangles)):<\/p>\n
    t1 = [src_points[triangles[i][0]], src_points[triangles[i][1]], src_points[triangles[i][2]]]<\/p>\n
    t2 = [dst_points[triangles[i][0]], dst_points[triangles[i][1]], dst_points[triangles[i][2]]]<\/p>\n
    warp_triangle(src_img, dst_img, t1, t2)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e94\u3001\u751f\u6210\u65b0\u8138\u90e8\u56fe\u50cf<\/h2>\n<\/p>\n
\u5728\u8fdb\u884c\u7279\u5f81\u66ff\u6362\u540e\uff0c\u9700\u8981\u751f\u6210\u65b0\u7684\u8138\u90e8\u56fe\u50cf\u3002\u8fd9\u4e2a\u8fc7\u7a0b\u53ef\u4ee5\u901a\u8fc7\u65e0\u7f1d\u514b\u9686\u6280\u672f\u6765\u5b9e\u73b0\u3002OpenCV\u63d0\u4f9b\u4e86seamlessClone\u51fd\u6570\uff0c\u53ef\u4ee5\u5c06\u6e90\u56fe\u50cf\u65e0\u7f1d\u5730\u514b\u9686\u5230\u76ee\u6807\u56fe\u50cf\u4e0a\u3002<\/p>\n<\/p>\n
# \u5b9a\u4e49\u4e2d\u5fc3\u70b9<\/p>\n
center = (dst_points[30][0], dst_points[30][1])<\/p>\n
\u751f\u6210\u65b0\u8138\u90e8\u56fe\u50cf<\/strong><\/h2>\n
output = cv2.seamlessClone(dst_img, target_frame, mask, center, cv2.NORMAL_CLONE)<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u516d\u3001\u5408\u6210\u65b0\u89c6\u9891<\/h2>\n<\/p>\n
\u6700\u540e\uff0c\u5c06\u751f\u6210\u7684\u65b0\u8138\u90e8\u56fe\u50cf\u5408\u6210\u5230\u89c6\u9891\u5e27\u4e2d\uff0c\u5e76\u4fdd\u5b58\u4e3a\u65b0\u89c6\u9891\u3002\u53ef\u4ee5\u4f7f\u7528OpenCV\u7684VideoWriter\u7c7b\u6765\u5b9e\u73b0\u3002<\/p>\n<\/p>\n
# \u5b9a\u4e49\u89c6\u9891\u5199\u5165\u5668<\/p>\n
output_video_path = 'output_video.mp4'<\/p>\n
fourcc = cv2.VideoWriter_fourcc(*'mp4v')<\/p>\n
out = cv2.VideoWriter(output_video_path, fourcc, 30.0, (frame_width, frame_height))<\/p>\n
\u5408\u6210\u65b0\u89c6\u9891<\/strong><\/h2>\n
while cap.isOpened():<\/p>\n
    ret, frame = cap.read()<\/p>\n
    if not ret:<\/p>\n
        break<\/p>\n
    # \u68c0\u6d4b\u4eba\u8138\u5e76\u66ff\u6362\u8138\u90e8\u7279\u5f81<\/p>\n
    # ...\uff08\u7701\u7565\u76f8\u540c\u7684\u4ee3\u7801\uff09<\/p>\n
    # \u5199\u5165\u65b0\u7684\u89c6\u9891\u5e27<\/p>\n
    out.write(output)<\/p>\n
cap.release()<\/p>\n
out.release()<\/p>\n
<\/code><\/pre>\n<\/p>\n
\u4e03\u3001\u4f18\u5316\u548c\u8c03\u8bd5<\/h2>\n<\/p>\n
\u5728\u5b9e\u9645\u5e94\u7528\u4e2d\uff0c\u4f60\u53ef\u80fd\u9700\u8981\u5bf9\u6bcf\u4e2a\u6b65\u9aa4\u8fdb\u884c\u4f18\u5316\u548c\u8c03\u8bd5\u3002\u6bd4\u5982\uff0c\u8c03\u6574\u4eba\u8138\u68c0\u6d4b\u5668\u7684\u53c2\u6570\uff0c\u4f7f\u7528\u66f4\u7cbe\u786e\u7684\u9762\u90e8\u5173\u952e\u70b9\u68c0\u6d4b\u6a21\u578b\uff0c\u6216\u8005\u6839\u636e\u5177\u4f53\u9700\u6c42\u8c03\u6574\u4eff\u5c04\u53d8\u6362\u548c\u65e0\u7f1d\u514b\u9686\u7684\u53c2\u6570\u3002<\/p>\n<\/p>\n
\u6b64\u5916\uff0c\u4e3a\u4e86\u63d0\u9ad8\u6362\u8138\u6548\u679c\uff0c\u4f60\u8fd8\u53ef\u4ee5\u8003\u8651\u4f7f\u7528\u4e00\u4e9b\u6df1\u5ea6\u5b66\u4e60\u6a21\u578b\uff0c\u5982GAN\uff08\u751f\u6210\u5bf9\u6297\u7f51\u7edc\uff09\u548cAutoencoder\uff08\u81ea\u7f16\u7801\u5668\uff09\u3002\u8fd9\u4e9b\u6a21\u578b\u53ef\u4ee5\u751f\u6210\u66f4\u52a0\u903c\u771f\u7684\u6362\u8138\u6548\u679c\uff0c\u4f46\u4e5f\u9700\u8981\u66f4\u591a\u7684\u8ba1\u7b97\u8d44\u6e90\u548c\u8bad\u7ec3\u6570\u636e\u3002<\/p>\n<\/p>\n
\u603b\u7ed3<\/h2>\n<\/p>\n
\u901a\u8fc7\u4e0a\u8ff0\u6b65\u9aa4\uff0c\u4f60\u53ef\u4ee5\u5728Python\u4e2d\u5b9e\u73b0\u89c6\u9891\u6362\u8138\u6280\u672f\u3002\u8fd9\u4e2a\u8fc7\u7a0b\u6d89\u53ca\u5230\u591a\u4e2a\u8ba1\u7b97\u673a\u89c6\u89c9\u548c\u56fe\u50cf\u5904\u7406\u6280\u672f\uff0c\u5305\u62ec\u4eba\u8138\u68c0\u6d4b\u3001\u4eba\u8138\u5bf9\u9f50\u3001\u7279\u5f81\u63d0\u53d6\u4e0e\u66ff\u6362\u3001\u751f\u6210\u65b0\u8138\u90e8\u56fe\u50cf\u548c\u5408\u6210\u65b0\u89c6\u9891\u3002\u5c3d\u7ba1\u8fd9\u4e9b\u6b65\u9aa4\u770b\u8d77\u6765\u6bd4\u8f83\u590d\u6742\uff0c\u4f46\u901a\u8fc7\u4e0d\u65ad\u5c1d\u8bd5\u548c\u8c03\u8bd5\uff0c\u4f60\u53ef\u4ee5\u9010\u6b65\u638c\u63e1\u5e76\u5b9e\u73b0\u9ad8\u8d28\u91cf\u7684\u89c6\u9891\u6362\u8138\u6548\u679c\u3002<\/p>\n<\/p>\n
\u76f8\u5173\u95ee\u7b54FAQs\uff1a<\/strong><\/h2>\n
 1. \u5982\u4f55\u4f7f\u7528Python\u8fdb\u884c\u4eba\u8138\u66ff\u6362\u7684\u57fa\u672c\u6b65\u9aa4\u662f\u4ec0\u4e48\uff1f<\/strong>
\u8fdb\u884c\u4eba\u8138\u66ff\u6362\u7684\u57fa\u672c\u6b65\u9aa4\u5305\u62ec\uff1a\u9996\u5148\uff0c\u4f7f\u7528OpenCV\u6216Dlib\u7b49\u5e93\u8fdb\u884c\u4eba\u8138\u68c0\u6d4b\u3002\u63a5\u7740\uff0c\u63d0\u53d6\u76ee\u6807\u4eba\u7269\u7684\u9762\u90e8\u7279\u5f81\uff0c\u5e76\u9009\u62e9\u8981\u66ff\u6362\u7684\u9762\u5b54\u3002\u4e4b\u540e\uff0c\u4f7f\u7528\u56fe\u50cf\u5904\u7406\u6280\u672f\u5c06\u9009\u5b9a\u7684\u4eba\u8138\u5408\u6210\u5230\u76ee\u6807\u89c6\u9891\u4e2d\u3002\u6700\u540e\uff0c\u751f\u6210\u65b0\u7684\u5e26\u6709\u66ff\u6362\u4eba\u8138\u7684\u89c6\u9891\u6587\u4ef6\u3002<\/p>\n
2. \u5728Python\u4e2d\uff0c\u6709\u54ea\u4e9b\u5e93\u53ef\u4ee5\u5e2e\u52a9\u5b9e\u73b0\u4eba\u8138\u6362\u8138\u7684\u529f\u80fd\uff1f<\/strong>
\u5e38\u7528\u7684Python\u5e93\u5305\u62ecOpenCV\u3001Dlib\u548cFaceSwap\u7b49\u3002OpenCV\u63d0\u4f9b\u4e86\u5f3a\u5927\u7684\u56fe\u50cf\u5904\u7406\u529f\u80fd\uff0cDlib\u5728\u9762\u90e8\u7279\u5f81\u63d0\u53d6\u65b9\u9762\u8868\u73b0\u4f18\u5f02\uff0c\u800cFaceSwap\u5219\u662f\u4e00\u4e2a\u4e13\u95e8\u7528\u4e8e\u4eba\u8138\u66ff\u6362\u7684\u5de5\u5177\uff0c\u80fd\u591f\u7b80\u5316\u6574\u4e2a\u8fc7\u7a0b\u3002<\/p>\n
3. \u4eba\u8138\u66ff\u6362\u8fc7\u7a0b\u4e2d\uff0c\u5982\u4f55\u786e\u4fdd\u6362\u8138\u6548\u679c\u81ea\u7136\uff1f<\/strong>
\u4e3a\u4e86\u786e\u4fdd\u6362\u8138\u6548\u679c\u81ea\u7136\uff0c\u53ef\u4ee5\u91c7\u53d6\u4ee5\u4e0b\u63aa\u65bd\uff1a\u9009\u62e9\u76f8\u4f3c\u89d2\u5ea6\u548c\u8868\u60c5\u7684\u4eba\u8138\uff0c\u8c03\u6574\u5149\u7167\u548c\u8272\u5f69\u5339\u914d\uff0c\u4f7f\u66ff\u6362\u7684\u4eba\u8138\u4e0e\u80cc\u666f\u65e0\u7f1d\u878d\u5408\u3002\u6b64\u5916\uff0c\u4f7f\u7528\u6df1\u5ea6\u5b66\u4e60\u6a21\u578b\u6765\u63d0\u9ad8\u4eba\u8138\u5408\u6210\u7684\u771f\u5b9e\u611f\u4e5f\u662f\u4e00\u4e2a\u6709\u6548\u7684\u65b9\u6cd5\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"\u5728Python\u4e2d\u5b9e\u73b0\u89c6\u9891\u6362\u8138\u6280\u672f\uff0c\u901a\u5e38\u9700\u8981\u4f7f\u7528\u4e00\u4e9b\u8ba1\u7b97\u673a\u89c6\u89c9\u5e93\u548c\u6df1\u5ea6\u5b66\u4e60\u6846\u67b6\u3002\u4e3b\u8981\u6b65\u9aa4\u5305\u62ec\uff1a\u4eba\u8138\u68c0\u6d4b\u3001\u4eba\u8138\u5bf9\u9f50 […]","protected":false},"author":3,"featured_media":1149911,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"footnotes":""},"categories":[37],"tags":[],"acf":[],"_links":{"self":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1149908"}],"collection":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/comments?post=1149908"}],"version-history":[{"count":"1","href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1149908\/revisions"}],"predecessor-version":[{"id":1149915,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/posts\/1149908\/revisions\/1149915"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media\/1149911"}],"wp:attachment":[{"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/media?parent=1149908"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/categories?post=1149908"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/docs.pingcode.com\/wp-json\/wp\/v2\/tags?post=1149908"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}