update

data/porter_tasks/porter_task_chenjieshen_douyin_video_to_bilibili.json

@@ -6,7 +6,7 @@
     "sec_user_id": "MS4wLjABAAAATGoBrO7yiJ3q9go4fxq9JXjrnP1bFpdkgKckC1IpfXA_vrjSmL9ZtjmTju8ApwbT",
     "check_interval": 900,
     "key_of_credentials": "douyin_wentao_credentials",
-    "min_date2": "2025-09-23 00:00:00",
+    "min_date": "2025-10-02 00:00:00",
     "output_video_dir": "data/tasks/chenjieshen_douyin_video_to_bilibili/video/douyin/陈杰森",
     "output_video_info_file": "data/tasks/chenjieshen_douyin_video_to_bilibili/video/douyin/陈杰森/file_info.json"
   },
@@ -17,7 +17,7 @@
     "sec_user_id": "MS4wLjABAAAA49QFP6YhorLIIX9M-FiZeKxmqhqXlttluSsZeaxvxzU",
     "check_interval": 900,
     "key_of_credentials": "douyin_wentao_credentials",
-    "min_date2": "2025-09-23 00:00:00",
+    "min_date": "2025-10-02 00:00:00",
     "output_video_dir": "data/tasks/chenjieshen_douyin_video_to_bilibili/video/douyin/陈杰森",
     "output_video_info_file": "data/tasks/chenjieshen_douyin_video_to_bilibili/video/douyin/陈杰森/file_info.json"
   },
@@ -31,6 +31,6 @@
     "target_user_id": "442286660",
     "key_of_credentials": "bilibili_chenjiesen_credentials",
     "remove_after_upload": true,
-    "min_date2": "2025-09-23 00:00:00"
+    "min_date": "2025-10-02 00:00:00"
   }
 ]

data/porter_tasks/porter_task_chenjieshen_douyin_video_to_youtube.json

@@ -6,7 +6,7 @@
     "sec_user_id": "MS4wLjABAAAATGoBrO7yiJ3q9go4fxq9JXjrnP1bFpdkgKckC1IpfXA_vrjSmL9ZtjmTju8ApwbT",
     "check_interval": 900,
     "key_of_credentials": "douyin_wentao_credentials",
-    "min_date2": "2025-09-23 00:00:00",
+    "min_date": "2025-10-02 00:00:00",
     "output_video_dir": "data/tasks/chenjieshen_douyin_video_to_youtube/video/douyin/陈杰森",
     "output_video_info_file": "data/tasks/chenjieshen_douyin_video_to_youtube/video/douyin/陈杰森/file_info.json"
   },
@@ -17,7 +17,7 @@
     "sec_user_id": "MS4wLjABAAAA49QFP6YhorLIIX9M-FiZeKxmqhqXlttluSsZeaxvxzU",
     "check_interval": 900,
     "key_of_credentials": "douyin_wentao_credentials",
-    "min_date2": "2025-09-23 00:00:00",
+    "min_date": "2025-10-02 00:00:00",
     "output_video_dir": "data/tasks/chenjieshen_douyin_video_to_youtube/video/douyin/陈杰森",
     "output_video_info_file": "data/tasks/chenjieshen_douyin_video_to_youtube/video/douyin/陈杰森/file_info.json"
   },
@@ -34,6 +34,6 @@
     "remove_after_upload_delay": 1,
     "playlist_title": "Short",
     "playlist_id": "PL1KtQ49rVMElugHudIdyKLAmgmMVdqoxQ",
-    "min_date2": "2025-09-23 00:00:00"
+    "min_date": "2025-10-02 00:00:00"
   }
 ]

toolbox/douyin/video/download.py

@@ -8,6 +8,7 @@ import logging
 from pathlib import Path
 from zoneinfo import ZoneInfo
 
+from gradio.cli.commands.deploy_space import readme_file
 from tenacity import before_sleep_log, retry, retry_if_exception_type, stop_after_attempt, wait_fixed
 
 from project_settings import project_path, time_zone_info
@@ -145,7 +146,7 @@ class VideoDownload(DouyinClient):
 
         stop_flag = False
         max_cursor = 0
-        for i in range(100):
+        for i in range(1000):
             if stop_flag:
                 break
             rows = await self.get_video_list_by_user_id(sec_user_id=sec_user_id, max_cursor=max_cursor, count=18)
@@ -184,6 +185,127 @@ class VideoDownload(DouyinClient):
                     result.append(task)
         return result
 
+    async def get_video_list_by_mix_id(self, mix_id: str, cursor: int = 0, count: int = 18):
+        url = "https://www.douyin.com/aweme/v1/web/mix/aweme/"
+
+        params = {
+            "device_platform": "webapp",
+            "aid": "6383",
+            "channel": "channel_pc_web",
+            "cursor": cursor,
+            "count": count,
+            "publish_video_strategy_type": "2",
+            "version_code": "290100",
+            "version_name": "29.1.0",
+
+            "mix_id": mix_id,
+        }
+
+        response = await self.async_session.request(
+            method="GET",
+            url=url,
+            headers={
+                **self.headers,
+                "referer": "https://www.douyin.com/",
+            },
+            params=params,
+        )
+        if response.status_code == 444:
+            # Access Denied
+            raise ExpectedError(status_code=60444, message=f"request failed, status_code: {response.status_code}, text: {response.text}")
+        elif response.status_code == 200 and len(response.text) == 0:
+            # Maybe Access Denied
+            raise ExpectedError(status_code=60444, message=f"request failed, status_code: {response.status_code}, text: {response.text}")
+        elif response.status_code != 200:
+            raise AssertionError(f"request failed, status_code: {response.status_code}, text: {response.text}")
+        elif response.text == "blocked":
+            raise AssertionError(f"request failed, status_code: {response.status_code}, text: {response.text}")
+        js = response.json()
+        aweme_list = js["aweme_list"]
+        if aweme_list is None:
+            return list()
+
+        result = list()
+        for aweme in aweme_list:
+            # aweme_ = json.dumps(aweme, ensure_ascii=False, indent=4)
+            # print(aweme_)
+
+            aweme_id = aweme["aweme_id"]
+            desc = aweme["desc"]
+            create_time = aweme["create_time"]
+            create_time_ = datetime.fromtimestamp(
+                create_time,
+                tz=ZoneInfo(time_zone_info)
+            )
+            create_time_str = create_time_.strftime("%Y%m%dT%H%M%S")
+
+            # video
+            video = aweme["video"]
+            url_list = video["play_addr"]["url_list"]
+
+            # tags
+            text_extra = aweme["text_extra"]
+            tags = set()
+            for t in text_extra:
+                tag = t.get("hashtag_name")
+                if tag is None:
+                    tag = t.get("search_text")
+                if tag is None:
+                    # print(t)
+                    continue
+                tags.add(tag)
+            tags = list(tags)
+
+            # title
+            title: str = desc
+            for tag in tags:
+                title = title.replace(f"#{tag}", "")
+                # title = title.replace(f"# {tag}", "")
+            title = title.strip()
+
+            row = {
+                "aweme_id": aweme_id,
+                "create_time": create_time,
+                "create_time_str": create_time_str,
+                "title": title,
+                "desc": desc,
+                "url_list": url_list,
+                "tags": tags,
+            }
+            result.append(row)
+        return result
+
+    async def get_all_video_by_mix_id(self, mix_id: str):
+        result = list()
+
+        cursor = 0
+        count = 18
+        for i in range(1000):
+            rows = await self.get_video_list_by_mix_id(mix_id=mix_id, cursor=cursor, count=count)
+            if len(rows) == 0:
+                break
+            cursor += count
+
+            for row in rows:
+                create_time = row["create_time"]
+                aweme_id = row["aweme_id"]
+                create_time_str = row["create_time_str"]
+                title = row["title"]
+                desc = row["desc"]
+                url_list = row["url_list"]
+                tags = row["tags"]
+
+                task = {
+                    "aweme_id": aweme_id,
+                    "create_time_str": create_time_str,
+                    "title": title,
+                    "desc": desc,
+                    "url_list": url_list,
+                    "tags": tags,
+                }
+                result.append(task)
+        return result
+
 
 def get_args():
     parser = argparse.ArgumentParser()
@@ -222,5 +344,55 @@ async def main():
     return
 
 
+async def main2():
+    import random
+    import re
+    import log
+    from project_settings import project_path, log_directory
+
+    log.setup_size_rotating(log_directory=log_directory)
+
+    args = get_args()
+
+    output_video_dir = Path("output_video_dir")
+    output_video_dir.mkdir(parents=True, exist_ok=True)
+    read_me_file = output_video_dir / "README.txt"
+
+    client = VideoDownload()
+
+    flag = client.check_login()
+    print(f"flag: {flag}")
+    client.login_with_credentials_file(args.credentials_file)
+    # client.login_with_qrcode_url()
+    flag = client.check_login()
+    print(f"flag: {flag}")
+
+    js = await client.get_all_video_by_mix_id(
+        mix_id="7337883410737661989",
+    )
+    print(f"count: {len(js)}")
+
+    with open(read_me_file.as_posix(), "w", encoding="utf-8") as f:
+        for row in js:
+            aweme_id = row["aweme_id"]
+            create_time_str = row["create_time_str"]
+            title = row["title"]
+            desc = row["desc"]
+            url_list = row["url_list"]
+            tags = row["tags"]
+            video_url = random.sample(url_list, k=1)[0]
+
+            title_ = re.sub(r'[\\/:*?"<>|]', '_', title)
+            title_ = title_[:50]
+            filename = output_video_dir / f"{aweme_id}_{create_time_str}_{title_}.mp4"
+            filename.parent.mkdir(parents=True, exist_ok=True)
+            await client.download_video_by_url(filename, video_url)
+
+            content = f"{title}\n{desc}\n{tags}"
+            f.write(f"{content}\n\n\n")
+            f.flush()
+    return
+
+
 if __name__ == "__main__":
-    asyncio.run(main())
+    asyncio.run(main2())

toolbox/douyin_selenium/tasks/bless_bag_collector.py

@@ -98,7 +98,7 @@ class BlessBagCollector(object):
         return element
 
     def get_bless_bag_card_button_element(self):
-        xpath = '//div[@id="lottery_close_cotainer"]//div[contains(text(), "一键发评论参与福袋") or contains(text(), "分享直播间") or contains(text(), "加入粉丝团（1钻)") or contains(text(), "已参与") or contains(text(), "知道了")]'
+        xpath = '//div[@id="lottery_close_cotainer"]//div[contains(text(), "一键发评论参与福袋") or contains(text(), "分享直播间") or contains(text(), "加入粉丝团（1钻)") or contains(text(), "已参与") or contains(text(), "知道了") or contains(text(), "提升亲密度")]'
         return self.get_element_by_xpath(xpath)
 
     def get_bless_bag_card_content_element(self):
@@ -256,6 +256,8 @@ class BlessBagCollector(object):
         elif bless_bag_card_content == "加入粉丝团（1钻)":
             self.sleep_by_bless_bag_countdown()
             # self.click_element(bless_bag_card_button_element)
+        elif bless_bag_card_content == "提升亲密度":
+            self.sleep_by_bless_bag_countdown()
         elif bless_bag_card_content == "已参与":
             self.try_to_close_bless_bag_card()
             self.sleep_by_bless_bag_countdown()