Update 3mergeDialogToVideo.py

3mergeDialogToVideo.py

@@ -33,6 +33,29 @@ print("azure key是",azure_speech_key)
 print("azure_service_region是",azure_service_region)
 print("my_openai_key",my_openai_key)
 
+
+from faker import Faker
+fake = Faker()
+fake_user_agent = fake.user_agent()
+fake_headers = {
+    'scheme': 'https',
+    'Accept': '*/*',
+    'Accept-Encoding': 'gzip, deflate, br, zstd',
+    'Accept-Language': 'zh-CN,zh;q=0.9',
+    'Dnt': '1',
+    'Priority': 'u=1, i',
+    'Sec-Ch-Ua': '"Chromium";v="124", "Google Chrome";v="124", "Not-A.Brand";v="99"',
+    'Sec-Ch-Ua-Mobile': '?0',
+    'Sec-Ch-Ua-Platform': '"Windows"',
+    'Sec-Fetch-Dest': 'empty',
+    'Sec-Fetch-Mode': 'cors',
+    'Sec-Fetch-Site': 'same-origin',
+    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36'
+}
+fake_headers['User-Agent'] = fake_user_agent
+
+
+
 #通过去水印完整漫画图片->获取相应的对话框图片->获取对话框文字->返回对话框文字
 def get_image_copywrite(image_path:"图片路径(包含后缀)",dialog_cut_path:"对话框切割路径")->"返回漫画关联对话框识别后得到的文案str(原文即可),也可能是none":
     def extract_chinese(text:str)->str:
@@ -204,31 +227,20 @@ def sort_dialog_list(sorted_indices:list,related_groups:list,sorted_coordinates)
     return filtered_data
 
 
-def get_sorted_dialog_text(image_path:"包含后缀的文件路径")->"返回排序后的text list(一列或者几列话,反正是一个框的内容,几句不清楚,一个框的list当一次文案就行)  或者失败请求返回none":
+def get_sorted_dialog_text(image_path:"包含后缀的文件路径",fake_headers:dict=None)->"返回排序后的text list(一列或者几列话,反正是一个框的内容,几句不清楚,一个框的list当一次文案就行)  或者失败请求返回none":
+
+    # 创建一个Session对象
+    session = requests.Session()
+    if fake_headers is not None:
+        session.headers = fake_headers
+        
     image_bytes = open(image_path, 'rb')
-    # headers = {
-    #     'authority': 'rogerxavier-fastapi-t5-magi.hf.space',
-    #     'scheme': 'https',
-    #     'Accept': '*/*',
-    #     'Accept-Encoding': 'gzip, deflate, br, zstd',
-    #     'Accept-Language': 'zh-CN,zh;q=0.9',
-    #     'Cookie': 'spaces-jwt=eyJhbGciOiJFZERTQSJ9.eyJyZWFkIjp0cnVlLCJwZXJtaXNzaW9ucyI6eyJyZXBvLmNvbnRlbnQucmVhZCI6dHJ1ZX0sIm9uQmVoYWxmT2YiOnsia2luZCI6InVzZXIiLCJfaWQiOiI2NDJhNTNiNTE2ZDRkODI5M2M5YjdiNzgiLCJ1c2VyIjoicm9nZXJ4YXZpZXIifSwiaWF0IjoxNzE2Njg3MzU3LCJzdWIiOiIvc3BhY2VzL3JvZ2VyeGF2aWVyL29jcl93aXRoX2Zhc3RhcGkiLCJleHAiOjE3MTY3NzM3NTcsImlzcyI6Imh0dHBzOi8vaHVnZ2luZ2ZhY2UuY28ifQ._sGdEgC-ijbIhLmB6iNSBQ_xHNzb4Ydb9mD0L3ByRmJSbB9ccfGbRgtNmkV1JLLldHp_VEKUSQt9Mwq_q4aGAQ',
-    #     'Dnt': '1',
-    #     'Priority': 'u=1, i',
-    #     'Sec-Ch-Ua': '"Chromium";v="124", "Google Chrome";v="124", "Not-A.Brand";v="99"',
-    #     'Sec-Ch-Ua-Mobile': '?0',
-    #     'Sec-Ch-Ua-Platform': '"Windows"',
-    #     'Sec-Fetch-Dest': 'empty',
-    #     'Sec-Fetch-Mode': 'cors',
-    #     'Sec-Fetch-Site': 'same-origin',
-    #     'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/124.0.0.0 Safari/537.36'
-    # }
+
     files = {
         "image": image_bytes,
     }
     try:
-        # resp = requests.post("https://rogerxavier-ocr-with-fastapi.hf.space/getCoordinates", files=files,headers=headers)#还是有header才能跑
-        resp = requests.post("https://rogerxavier-ocr-with-fastapi.hf.space/getCoordinates", files=files)#不用header看看会不会还限制
+        resp = session.post("https://rogerxavier-ocr-with-fastapi.hf.space/getCoordinates", files=files)#用faker header看看会不会还限制
         #先json转换，0为坐标list合集,1为 boxid和text合集
         boxCoordinates , boxInfo = resp.json()[0],resp.json()[1] #分别是list和dict类型
         print("ofa ocr识别漫画块成功返回")
@@ -249,9 +261,6 @@ def get_sorted_dialog_text(image_path:"包含后缀的文件路径")->"返回排
 
         # 调用函数并打印结果
         associate_text_list,related_groups = find_associate_text(sorted_indices,centers,sorted_coordinates,boxInfo)
-        #print("相关list是",associate_text_list)
-        #print("related_groups是",related_groups)
-        #print("sorted_indices是",sorted_indices)
 
         related_groups = sort_associate_text_list(sorted_indices,related_groups,boxCoordinates,centers)
 
@@ -473,20 +482,6 @@ if __name__ == '__main__':
             if filename is not None:
                 print("存放临时mp3文件的路径是",filename)
 
-                #含字幕版
-                # clip = ImageClip(img).set_duration(duration).resize((width, height))  # 初始clip
-    
-                # txt_clip = TextClip(cur_copywrite, fontsize=40, color='white', bg_color='black',
-                #                     font=font_path)  ##文本clip后加入视频
-    
-                # txt_clip = txt_clip.set_pos(('center', 'bottom')).set_duration(duration)
-                # # 创建音频剪辑
-                # audio_clip = AudioFileClip(filename)
-                # clip = clip.set_audio(audio_clip)  # 将音频与视频片段关联
-                # clip = CompositeVideoClip([clip, txt_clip])
-                # video_clips.append(clip)
-                #含字幕版
-
                 #不含字幕版
                 clip = ImageClip(img).set_duration(duration).resize((width, height))