The configuration file supports URL crawling

Feature/config refactor 20251018

Author: NanmiCoder

config/base_config.py

@@ -38,7 +38,7 @@
 # 是否启用CDP模式 - 使用用户现有的Chrome/Edge浏览器进行爬取，提供更好的反检测能力
 # 启用后将自动检测并启动用户的Chrome/Edge浏览器，通过CDP协议进行控制
 # 这种方式使用真实的浏览器环境，包括用户的扩展、Cookie和设置，大大降低被检测的风险
-ENABLE_CDP_MODE = False
+ENABLE_CDP_MODE = True
 
 # CDP调试端口，用于与浏览器通信
 # 如果端口被占用，系统会自动尝试下一个可用端口

config/bilibili_config.py

@@ -13,16 +13,23 @@
 # 每天爬取视频/帖子的数量控制
 MAX_NOTES_PER_DAY = 1
 
-# 指定B站视频ID列表
+# 指定B站视频URL列表 (支持完整URL或BV号)
+# 示例:
+# - 完整URL: "https://www.bilibili.com/video/BV1dwuKzmE26/?spm_id_from=333.1387.homepage.video_card.click"
+# - BV号: "BV1d54y1g7db"
 BILI_SPECIFIED_ID_LIST = [
-    "BV1d54y1g7db",
+    "https://www.bilibili.com/video/BV1dwuKzmE26/?spm_id_from=333.1387.homepage.video_card.click",
     "BV1Sz4y1U77N",
     "BV14Q4y1n7jz",
     # ........................
 ]
 
-# 指定B站用户ID列表
+# 指定B站创作者URL列表 (支持完整URL或UID)
+# 示例:
+# - 完整URL: "https://space.bilibili.com/434377496?spm_id_from=333.1007.0.0"
+# - UID: "20813884"
 BILI_CREATOR_ID_LIST = [
+    "https://space.bilibili.com/434377496?spm_id_from=333.1007.0.0",
     "20813884",
     # ........................
 ]

config/dy_config.py

@@ -11,15 +11,27 @@
 # 抖音平台配置
 PUBLISH_TIME_TYPE = 0
 
-# 指定DY视频ID列表
+# 指定DY视频URL列表 (支持多种格式)
+# 支持格式:
+# 1. 完整视频URL: "https://www.douyin.com/video/7525538910311632128"
+# 2. 带modal_id的URL: "https://www.douyin.com/user/xxx?modal_id=7525538910311632128"
+# 3. 搜索页带modal_id: "https://www.douyin.com/root/search/python?modal_id=7525538910311632128"
+# 4. 短链接: "https://v.douyin.com/drIPtQ_WPWY/"
+# 5. 纯视频ID: "7280854932641664319"
 DY_SPECIFIED_ID_LIST = [
-    "7280854932641664319",
-    "7202432992642387233",
+    "https://www.douyin.com/video/7525538910311632128",
+    "https://v.douyin.com/drIPtQ_WPWY/",
+    "https://www.douyin.com/user/MS4wLjABAAAATJPY7LAlaa5X-c8uNdWkvz0jUGgpw4eeXIwu_8BhvqE?from_tab_name=main&modal_id=7525538910311632128",
+    "7202432992642387233",    
     # ........................
 ]
 
-# 指定DY用户ID列表
+# 指定DY创作者URL列表 (支持完整URL或sec_user_id)
+# 支持格式:
+# 1. 完整创作者主页URL: "https://www.douyin.com/user/MS4wLjABAAAATJPY7LAlaa5X-c8uNdWkvz0jUGgpw4eeXIwu_8BhvqE?from_tab_name=main"
+# 2. sec_user_id: "MS4wLjABAAAATJPY7LAlaa5X-c8uNdWkvz0jUGgpw4eeXIwu_8BhvqE"
 DY_CREATOR_ID_LIST = [
-    "MS4wLjABAAAATJPY7LAlaa5X-c8uNdWkvz0jUGgpw4eeXIwu_8BhvqE",
+    "https://www.douyin.com/user/MS4wLjABAAAATJPY7LAlaa5X-c8uNdWkvz0jUGgpw4eeXIwu_8BhvqE?from_tab_name=main",
+    "MS4wLjABAAAATJPY7LAlaa5X-c8uNdWkvz0jUGgpw4eeXIwu_8BhvqE"
     # ........................
 ]

config/ks_config.py

@@ -10,11 +10,22 @@
 
 # 快手平台配置
 
-# 指定快手视频ID列表
-KS_SPECIFIED_ID_LIST = ["3xf8enb8dbj6uig", "3x6zz972bchmvqe"]
+# 指定快手视频URL列表 (支持完整URL或纯ID)
+# 支持格式:
+# 1. 完整视频URL: "https://www.kuaishou.com/short-video/3x3zxz4mjrsc8ke?authorId=3x84qugg4ch9zhs&streamSource=search"
+# 2. 纯视频ID: "3xf8enb8dbj6uig"
+KS_SPECIFIED_ID_LIST = [
+    "https://www.kuaishou.com/short-video/3x3zxz4mjrsc8ke?authorId=3x84qugg4ch9zhs&streamSource=search&area=searchxxnull&searchKey=python",
+    "3xf8enb8dbj6uig",
+    # ........................
+]
 
-# 指定快手用户ID列表
+# 指定快手创作者URL列表 (支持完整URL或纯ID)
+# 支持格式:
+# 1. 创作者主页URL: "https://www.kuaishou.com/profile/3x84qugg4ch9zhs"
+# 2. 纯user_id: "3x4sm73aye7jq7i"
 KS_CREATOR_ID_LIST = [
+    "https://www.kuaishou.com/profile/3x84qugg4ch9zhs",
     "3x4sm73aye7jq7i",
     # ........................
 ]

config/xhs_config.py

@@ -21,8 +21,12 @@
     # ........................
 ]
 
-# 指定用户ID列表
+# 指定创作者URL列表 (支持完整URL或纯ID)
+# 支持格式:
+# 1. 完整创作者主页URL (带xsec_token和xsec_source参数): "https://www.xiaohongshu.com/user/profile/5eb8e1d400000000010075ae?xsec_token=AB1nWBKCo1vE2HEkfoJUOi5B6BE5n7wVrbdpHoWIj5xHw=&xsec_source=pc_feed"
+# 2. 纯user_id: "63e36c9a000000002703502b"
 XHS_CREATOR_ID_LIST = [
-    "63e36c9a000000002703502b",
+    "https://www.xiaohongshu.com/user/profile/5eb8e1d400000000010075ae?xsec_token=AB1nWBKCo1vE2HEkfoJUOi5B6BE5n7wVrbdpHoWIj5xHw=&xsec_source=pc_feed",
+    "63e36c9a000000002703502b",    
     # ........................
 ]

media_platform/bilibili/core.py

@@ -41,6 +41,7 @@
 from .client import BilibiliClient
 from .exception import DataFetchError
 from .field import SearchOrderType
+from .help import parse_video_info_from_url, parse_creator_info_from_url
 from .login import BilibiliLogin
 
 
@@ -103,8 +104,14 @@ async def start(self):
                 await self.get_specified_videos(config.BILI_SPECIFIED_ID_LIST)
             elif config.CRAWLER_TYPE == "creator":
                 if config.CREATOR_MODE:
-                    for creator_id in config.BILI_CREATOR_ID_LIST:
-                        await self.get_creator_videos(int(creator_id))
+                    for creator_url in config.BILI_CREATOR_ID_LIST:
+                        try:
+                            creator_info = parse_creator_info_from_url(creator_url)
+                            utils.logger.info(f"[BilibiliCrawler.start] Parsed creator ID: {creator_info.creator_id} from {creator_url}")
+                            await self.get_creator_videos(int(creator_info.creator_id))
+                        except ValueError as e:
+                            utils.logger.error(f"[BilibiliCrawler.start] Failed to parse creator URL: {e}")
+                            continue
                 else:
                     await self.get_all_creator_details(config.BILI_CREATOR_ID_LIST)
             else:
@@ -362,11 +369,23 @@ async def get_creator_videos(self, creator_id: int):
             utils.logger.info(f"[BilibiliCrawler.get_creator_videos] Sleeping for {config.CRAWLER_MAX_SLEEP_SEC} seconds after page {pn}")
             pn += 1
 
-    async def get_specified_videos(self, bvids_list: List[str]):
+    async def get_specified_videos(self, video_url_list: List[str]):
         """
-        get specified videos info
+        get specified videos info from URLs or BV IDs
+        :param video_url_list: List of video URLs or BV IDs
         :return:
         """
+        utils.logger.info("[BilibiliCrawler.get_specified_videos] Parsing video URLs...")
+        bvids_list = []
+        for video_url in video_url_list:
+            try:
+                video_info = parse_video_info_from_url(video_url)
+                bvids_list.append(video_info.video_id)
+                utils.logger.info(f"[BilibiliCrawler.get_specified_videos] Parsed video ID: {video_info.video_id} from {video_url}")
+            except ValueError as e:
+                utils.logger.error(f"[BilibiliCrawler.get_specified_videos] Failed to parse video URL: {e}")
+                continue
+
         semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
         task_list = [self.get_video_info_task(aid=0, bvid=video_id, semaphore=semaphore) for video_id in bvids_list]
         video_details = await asyncio.gather(*task_list)
@@ -568,18 +587,30 @@ async def get_bilibili_video(self, video_item: Dict, semaphore: asyncio.Semaphor
         extension_file_name = f"video.mp4"
         await bilibili_store.store_video(aid, content, extension_file_name)
 
-    async def get_all_creator_details(self, creator_id_list: List[int]):
+    async def get_all_creator_details(self, creator_url_list: List[str]):
         """
-        creator_id_list: get details for creator from creator_id_list
+        creator_url_list: get details for creator from creator URL list
         """
-        utils.logger.info(f"[BilibiliCrawler.get_creator_details] Crawling the detalis of creator")
-        utils.logger.info(f"[BilibiliCrawler.get_creator_details] creator ids:{creator_id_list}")
+        utils.logger.info(f"[BilibiliCrawler.get_all_creator_details] Crawling the details of creators")
+        utils.logger.info(f"[BilibiliCrawler.get_all_creator_details] Parsing creator URLs...")
+
+        creator_id_list = []
+        for creator_url in creator_url_list:
+            try:
+                creator_info = parse_creator_info_from_url(creator_url)
+                creator_id_list.append(int(creator_info.creator_id))
+                utils.logger.info(f"[BilibiliCrawler.get_all_creator_details] Parsed creator ID: {creator_info.creator_id} from {creator_url}")
+            except ValueError as e:
+                utils.logger.error(f"[BilibiliCrawler.get_all_creator_details] Failed to parse creator URL: {e}")
+                continue
+
+        utils.logger.info(f"[BilibiliCrawler.get_all_creator_details] creator ids:{creator_id_list}")
 
         semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
         task_list: List[Task] = []
         try:
             for creator_id in creator_id_list:
-                task = asyncio.create_task(self.get_creator_details(creator_id, semaphore), name=creator_id)
+                task = asyncio.create_task(self.get_creator_details(creator_id, semaphore), name=str(creator_id))
                 task_list.append(task)
         except Exception as e:
             utils.logger.warning(f"[BilibiliCrawler.get_all_creator_details] error in the task list. The creator will not be included. {e}")

media_platform/bilibili/help.py

@@ -9,15 +9,17 @@
 # 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。  
 
 
-    # -*- coding: utf-8 -*-
+# -*- coding: utf-8 -*-
 # @Author  : [email protected]
 # @Time    : 2023/12/2 23:26
 # @Desc    : bilibili 请求参数签名
 # 逆向实现参考：https://socialsisteryi.github.io/bilibili-API-collect/docs/misc/sign/wbi.html#wbi%E7%AD%BE%E5%90%8D%E7%AE%97%E6%B3%95
+import re
 import urllib.parse
 from hashlib import md5
 from typing import Dict
 
+from model.m_bilibili import VideoUrlInfo, CreatorUrlInfo
 from tools import utils
 
 
@@ -66,16 +68,71 @@ def sign(self, req_data: Dict) -> Dict:
         return req_data
 
 
+def parse_video_info_from_url(url: str) -> VideoUrlInfo:
+    """
+    从B站视频URL中解析出视频ID
+    Args:
+        url: B站视频链接
+            - https://www.bilibili.com/video/BV1dwuKzmE26/?spm_id_from=333.1387.homepage.video_card.click
+            - https://www.bilibili.com/video/BV1d54y1g7db
+            - BV1d54y1g7db (直接传入BV号)
+    Returns:
+        VideoUrlInfo: 包含视频ID的对象
+    """
+    # 如果传入的已经是BV号,直接返回
+    if url.startswith("BV"):
+        return VideoUrlInfo(video_id=url)
+
+    # 使用正则表达式提取BV号
+    # 匹配 /video/BV... 或 /video/av... 格式
+    bv_pattern = r'/video/(BV[a-zA-Z0-9]+)'
+    match = re.search(bv_pattern, url)
+
+    if match:
+        video_id = match.group(1)
+        return VideoUrlInfo(video_id=video_id)
+
+    raise ValueError(f"无法从URL中解析出视频ID: {url}")
+
+
+def parse_creator_info_from_url(url: str) -> CreatorUrlInfo:
+    """
+    从B站创作者空间URL中解析出创作者ID
+    Args:
+        url: B站创作者空间链接
+            - https://space.bilibili.com/434377496?spm_id_from=333.1007.0.0
+            - https://space.bilibili.com/20813884
+            - 434377496 (直接传入UID)
+    Returns:
+        CreatorUrlInfo: 包含创作者ID的对象
+    """
+    # 如果传入的已经是纯数字ID,直接返回
+    if url.isdigit():
+        return CreatorUrlInfo(creator_id=url)
+
+    # 使用正则表达式提取UID
+    # 匹配 /space.bilibili.com/数字 格式
+    uid_pattern = r'space\.bilibili\.com/(\d+)'
+    match = re.search(uid_pattern, url)
+
+    if match:
+        creator_id = match.group(1)
+        return CreatorUrlInfo(creator_id=creator_id)
+
+    raise ValueError(f"无法从URL中解析出创作者ID: {url}")
+
+
 if __name__ == '__main__':
-    _img_key = "7cd084941338484aae1ad9425b84077c"
-    _sub_key = "4932caff0ff746eab6f01bf08b70ac45"
-    _search_url = "__refresh__=true&_extra=&ad_resource=5654&category_id=&context=&dynamic_offset=0&from_source=&from_spmid=333.337&gaia_vtoken=&highlight=1&keyword=python&order=click&page=1&page_size=20&platform=pc&qv_id=OQ8f2qtgYdBV1UoEnqXUNUl8LEDAdzsD&search_type=video&single_column=0&source_tag=3&web_location=1430654"
-    _req_data = dict()
-    for params in _search_url.split("&"):
-        kvalues = params.split("=")
-        key = kvalues[0]
-        value = kvalues[1]
-        _req_data[key] = value
-    print("pre req_data", _req_data)
-    _req_data = BilibiliSign(img_key=_img_key, sub_key=_sub_key).sign(req_data={"aid":170001})
-    print(_req_data)
+    # 测试视频URL解析
+    video_url1 = "https://www.bilibili.com/video/BV1dwuKzmE26/?spm_id_from=333.1387.homepage.video_card.click"
+    video_url2 = "BV1d54y1g7db"
+    print("视频URL解析测试:")
+    print(f"URL1: {video_url1} -> {parse_video_info_from_url(video_url1)}")
+    print(f"URL2: {video_url2} -> {parse_video_info_from_url(video_url2)}")
+
+    # 测试创作者URL解析
+    creator_url1 = "https://space.bilibili.com/434377496?spm_id_from=333.1007.0.0"
+    creator_url2 = "20813884"
+    print("\n创作者URL解析测试:")
+    print(f"URL1: {creator_url1} -> {parse_creator_info_from_url(creator_url1)}")
+    print(f"URL2: {creator_url2} -> {parse_creator_info_from_url(creator_url2)}")

media_platform/douyin/client.py

@@ -324,3 +324,28 @@ async def get_aweme_media(self, url: str) -> Union[bytes, None]:
             except httpx.HTTPError as exc:  # some wrong when call httpx.request method, such as connection error, client error, server error or response status code is not 2xx
                 utils.logger.error(f"[DouYinClient.get_aweme_media] {exc.__class__.__name__} for {exc.request.url} - {exc}")  # 保留原始异常类型名称，以便开发者调试
                 return None
+
+    async def resolve_short_url(self, short_url: str) -> str:
+        """
+        解析抖音短链接,获取重定向后的真实URL
+        Args:
+            short_url: 短链接,如 https://v.douyin.com/iF12345ABC/
+        Returns:
+            重定向后的完整URL
+        """
+        async with httpx.AsyncClient(proxy=self.proxy, follow_redirects=False) as client:
+            try:
+                utils.logger.info(f"[DouYinClient.resolve_short_url] Resolving short URL: {short_url}")
+                response = await client.get(short_url, timeout=10)
+
+                # 短链接通常返回302重定向
+                if response.status_code in [301, 302, 303, 307, 308]:
+                    redirect_url = response.headers.get("Location", "")
+                    utils.logger.info(f"[DouYinClient.resolve_short_url] Resolved to: {redirect_url}")
+                    return redirect_url
+                else:
+                    utils.logger.warning(f"[DouYinClient.resolve_short_url] Unexpected status code: {response.status_code}")
+                    return ""
+            except Exception as e:
+                utils.logger.error(f"[DouYinClient.resolve_short_url] Failed to resolve short URL: {e}")
+                return ""