feat:ins爬虫数据条件过滤优化

config/settings.py

@@ -9,7 +9,7 @@ def get_base_url():
 
 def get_base_file_url():
     # return "http://192.168.0.118:8186/"
-    return "/"
+    return "/files/reptile_data/"
 
 def get_account(name):
     data = {}

pc_facebook.py

@@ -117,7 +117,7 @@ def reptile(browser=None, search_word=""):
                 status = download_image(element['src'], download_dir)
                 if status:
                     element['src'] = access_address
-                    picture_url.append(access_address)
+                    picture_url.append(download_dir)
         else:
             print("")
         content = soup.prettify()

pc_instagram.py

@@ -122,7 +122,7 @@ def reptile(browser=None, search_word=""):
                 img_soup["src"] = access_address
                 # print(img_soup.prettify())
                 soup.append(img_soup)
-                picture_url.append(access_address)
+                picture_url.append(download_dir)
 
         content = soup.prettify()
         # 类型

pc_ptt.py

@@ -138,7 +138,7 @@ def reptile(browser=None, search_word=""):
                             status = download_image(element['src'], download_dir)
                             if status:
                                 element['src'] = access_address
-                                picture_url.append(access_address)
+                                picture_url.append(download_dir)
                     else:
                         print("")
                     # ---------------- 判断类型 end ----------

pc_twitter.py

@@ -117,7 +117,7 @@ def reptile(browser=None, search_word=""):
                 status = download_image(element['src'], download_dir)
                 if status:
                     element['src'] = access_address
-                    picture_url.append(access_address)
+                    picture_url.append(download_dir)
         else:
             print("")
         content = soup.prettify()

pc_youtube.py

@@ -47,16 +47,20 @@ def reptile(browser=None, search_word=""):
                 releaseTime = str(int(convert_string_to_time(element_time_list[index].text)))
             except:
                 releaseTime = str(int(time.time()))
+            video_url = []
+            # 下载地址
+            download_dir = f'{os.path.join(file_dir, f"{id}.mp4")}'
+            # 访问地址
+            access_address = f'{get_base_file_url()}{table_name.split("_")[1]}/{id}.mp4'
             # 下载视频
             state_download = yt_dlp_download(url, 'youtube')
-            log.debug(url)
-            file_http_src = f'{base_urr}youtube/{id}.mp4'
+            video_url.append(download_dir)
             if state_download:
                 # 组装数据
                 obj = {
                     "title": title,
-                    "content": f"<video controls style='width:100%' src='{file_http_src}'></video>",
-                    "videoUrl": file_http_src,
+                    "content": f"<video controls style='width:100%' src='{access_address}'></video>",
+                    "videoUrl": ",".join(video_url),
                     "link": link,
                     "reptileTime": str(int(time.time())),
                     "type": '视频',