Merge pull request #652 from gaoxiaobei/dev

feat(bilibili): Add flexible search modes and fix limit logic

Author: NanmiCoder

config/__init__.py

@@ -10,4 +10,4 @@
 
 
 from .base_config import *
-from .db_config import *
+from .db_config import *

config/base_config.py

@@ -10,28 +10,16 @@
 
 
 # 基础配置
-PLATFORM = "xhs"
+PLATFORM = "xhs" # 平台，xhs | dy | ks | bili | wb | tieba | zhihu
 KEYWORDS = "编程副业,编程兼职"  # 关键词搜索配置，以英文逗号分隔
 LOGIN_TYPE = "qrcode"  # qrcode or phone or cookie
 COOKIES = ""
-# 具体值参见media_platform.xxx.field下的枚举值，暂时只支持小红书
-SORT_TYPE = "popularity_descending"
-# 具体值参见media_platform.xxx.field下的枚举值，暂时只支持抖音
-PUBLISH_TIME_TYPE = 0
 CRAWLER_TYPE = (
     "search"  # 爬取类型，search(关键词搜索) | detail(帖子详情)| creator(创作者主页数据)
 )
-# 微博搜索类型 default (综合) | real_time (实时) | popular (热门) | video (视频)
-WEIBO_SEARCH_TYPE = "popular"
-# 自定义User Agent（暂时仅对XHS有效）
-UA = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36 Edg/131.0.0.0"
-
 # 是否开启 IP 代理
 ENABLE_IP_PROXY = False
 
-# 未启用代理时的最大爬取间隔，单位秒（暂时仅对XHS有效）
-CRAWLER_MAX_SLEEP_SEC = 2
-
 # 代理IP池数量
 IP_PROXY_POOL_COUNT = 2
 
@@ -102,101 +90,6 @@
 # 老版本项目使用了 db, 则需参考 schema/tables.sql line 287 增加表字段
 ENABLE_GET_SUB_COMMENTS = False
 
-# 已废弃⚠️⚠️⚠️指定小红书需要爬虫的笔记ID列表
-# 已废弃⚠️⚠️⚠️ 指定笔记ID笔记列表会因为缺少xsec_token和xsec_source参数导致爬取失败
-# XHS_SPECIFIED_ID_LIST = [
-#     "66fad51c000000001b0224b8",
-#     # ........................
-# ]
-
-# 指定小红书需要爬虫的笔记URL列表, 目前要携带xsec_token和xsec_source参数
-XHS_SPECIFIED_NOTE_URL_LIST = [
-    "https://www.xiaohongshu.com/explore/66fad51c000000001b0224b8?xsec_token=AB3rO-QopW5sgrJ41GwN01WCXh6yWPxjSoFI9D5JIMgKw=&xsec_source=pc_search"
-    # ........................
-]
-
-# 指定抖音需要爬取的ID列表
-DY_SPECIFIED_ID_LIST = [
-    "7280854932641664319",
-    "7202432992642387233",
-    # ........................
-]
-
-# 指定快手平台需要爬取的ID列表
-KS_SPECIFIED_ID_LIST = ["3xf8enb8dbj6uig", "3x6zz972bchmvqe"]
-
-# 指定B站平台需要爬取的视频bvid列表
-BILI_SPECIFIED_ID_LIST = [
-    "BV1d54y1g7db",
-    "BV1Sz4y1U77N",
-    "BV14Q4y1n7jz",
-    # ........................
-]
-
-# 指定微博平台需要爬取的帖子列表
-WEIBO_SPECIFIED_ID_LIST = [
-    "4982041758140155",
-    # ........................
-]
-
-# 指定weibo创作者ID列表
-WEIBO_CREATOR_ID_LIST = [
-    "5533390220",
-    # ........................
-]
-
-# 指定贴吧需要爬取的帖子列表
-TIEBA_SPECIFIED_ID_LIST = []
-
-# 指定贴吧名称列表，爬取该贴吧下的帖子
-TIEBA_NAME_LIST = [
-    # "盗墓笔记"
-]
-
-# 指定贴吧创作者URL列表
-TIEBA_CREATOR_URL_LIST = [
-    "https://tieba.baidu.com/home/main/?id=tb.1.7f139e2e.6CyEwxu3VJruH_-QqpCi6g&fr=frs",
-    # ........................
-]
-
-# 指定小红书创作者ID列表
-XHS_CREATOR_ID_LIST = [
-    "63e36c9a000000002703502b",
-    # ........................
-]
-
-# 指定Dy创作者ID列表(sec_id)
-DY_CREATOR_ID_LIST = [
-    "MS4wLjABAAAATJPY7LAlaa5X-c8uNdWkvz0jUGgpw4eeXIwu_8BhvqE",
-    # ........................
-]
-
-# 指定bili创作者ID列表(sec_id)
-BILI_CREATOR_ID_LIST = [
-    "20813884",
-    # ........................
-]
-
-# 指定快手创作者ID列表
-KS_CREATOR_ID_LIST = [
-    "3x4sm73aye7jq7i",
-    # ........................
-]
-
-
-# 指定知乎创作者主页url列表
-ZHIHU_CREATOR_URL_LIST = [
-    "https://www.zhihu.com/people/yd1234567",
-    # ........................
-]
-
-# 指定知乎需要爬取的帖子ID列表
-ZHIHU_SPECIFIED_ID_LIST = [
-    "https://www.zhihu.com/question/826896610/answer/4885821440",  # 回答
-    "https://zhuanlan.zhihu.com/p/673461588",  # 文章
-    "https://www.zhihu.com/zvideo/1539542068422144000",  # 视频
-]
-
 # 词云相关
 # 是否开启生成评论词云图
 ENABLE_GET_WORDCLOUD = False
@@ -212,27 +105,3 @@
 
 # 中文字体文件路径
 FONT_PATH = "./docs/STZHONGS.TTF"
-
-# 爬取开始的天数，仅支持 bilibili 关键字搜索，YYYY-MM-DD 格式，若为 None 则表示不设置时间范围，按照默认关键字最多返回 1000 条视频的结果处理
-START_DAY = "2024-01-01"
-
-# 爬取结束的天数，仅支持 bilibili 关键字搜索，YYYY-MM-DD 格式，若为 None 则表示不设置时间范围，按照默认关键字最多返回 1000 条视频的结果处理
-END_DAY = "2024-01-01"
-
-# 是否开启按每一天进行爬取的选项，仅支持 bilibili 关键字搜索
-# 若为 False，则忽略 START_DAY 与 END_DAY 设置的值
-# 若为 True，则按照 START_DAY 至 END_DAY 按照每一天进行筛选，这样能够突破 1000 条视频的限制，最大程度爬取该关键词下的所有视频
-ALL_DAY = False
-
-#!!! 下面仅支持 bilibili creator搜索
-# 爬取评论creator主页还是爬取creator动态和关系列表(True为前者)
-CREATOR_MODE = True
-
-# 爬取creator粉丝列表时起始爬取页数
-START_CONTACTS_PAGE = 1
-
-# 爬取作者粉丝和关注列表数量控制(单作者)
-CRAWLER_MAX_CONTACTS_COUNT_SINGLENOTES = 100
-
-# 爬取作者动态数量控制(单作者)
-CRAWLER_MAX_DYNAMICS_COUNT_SINGLENOTES = 50

main.py

@@ -45,25 +45,30 @@ def create_crawler(platform: str) -> AbstractCrawler:
         return crawler_class()
 
 async def main():
+    # Init crawler
+    crawler: Optional[AbstractCrawler] = None
+    try:
+        # parse cmd
+        await cmd_arg.parse_cmd()
 
-    # parse cmd
-    await cmd_arg.parse_cmd()
-
-    # init db
-    if config.SAVE_DATA_OPTION in ["db", "sqlite"]:
-        await db.init_db()
+        # init db
+        if config.SAVE_DATA_OPTION in ["db", "sqlite"]:
+            await db.init_db()
 
-    crawler = CrawlerFactory.create_crawler(platform=config.PLATFORM)
-    await crawler.start()
+        crawler = CrawlerFactory.create_crawler(platform=config.PLATFORM)
+        await crawler.start()
 
-    if config.SAVE_DATA_OPTION in ["db", "sqlite"]:
-        await db.close()
+    finally:
+        if crawler:
+            await crawler.close()
 
-    
+        if config.SAVE_DATA_OPTION in ["db", "sqlite"]:
+            await db.close()
 
 if __name__ == '__main__':
     try:
         # asyncio.run(main())
         asyncio.get_event_loop().run_until_complete(main())
     except KeyboardInterrupt:
+        print("\n[main] Caught keyboard interrupt, exiting.")
         sys.exit()

media_platform/bilibili/client.py

@@ -15,6 +15,7 @@
 # @Desc    : bilibili 请求客户端
 import asyncio
 import json
+import random
 from typing import Any, Callable, Dict, List, Optional, Tuple, Union
 from urllib.parse import urlencode
 
@@ -53,7 +54,11 @@ async def request(self, method, url, **kwargs) -> Any:
                 method, url, timeout=self.timeout,
                 **kwargs
             )
-        data: Dict = response.json()
+        try:
+            data: Dict = response.json()
+        except json.JSONDecodeError:
+            utils.logger.error(f"[BilibiliClient.request] Failed to decode JSON from response. status_code: {response.status_code}, response_text: {response.text}")
+            raise DataFetchError(f"Failed to decode JSON, content: {response.text}")
         if data.get("code") != 0:
             raise DataFetchError(data.get("message", "unkonw error"))
         else:
@@ -78,8 +83,12 @@ async def get_wbi_keys(self) -> Tuple[str, str]:
         :return:
         """
         local_storage = await self.playwright_page.evaluate("() => window.localStorage")
-        wbi_img_urls = local_storage.get("wbi_img_urls", "") or local_storage.get(
-            "wbi_img_url") + "-" + local_storage.get("wbi_sub_url")
+        wbi_img_urls = local_storage.get("wbi_img_urls", "")
+        if not wbi_img_urls:
+            img_url_from_storage = local_storage.get("wbi_img_url")
+            sub_url_from_storage = local_storage.get("wbi_sub_url")
+            if img_url_from_storage and sub_url_from_storage:
+                wbi_img_urls = f"{img_url_from_storage}-{sub_url_from_storage}"
         if wbi_img_urls and "-" in wbi_img_urls:
             img_url, sub_url = wbi_img_urls.split("-")
         else:
@@ -235,16 +244,50 @@ async def get_video_all_comments(self, video_id: str, crawl_interval: float = 1.
 
         :return:
         """
-
         result = []
         is_end = False
         next_page = 0
+        max_retries = 3
         while not is_end and len(result) < max_count:
-            comments_res = await self.get_video_comments(video_id, CommentOrderType.DEFAULT, next_page)
+            comments_res = None
+            for attempt in range(max_retries):
+                try:
+                    comments_res = await self.get_video_comments(video_id, CommentOrderType.DEFAULT, next_page)
+                    break  # Success
+                except DataFetchError as e:
+                    if attempt < max_retries - 1:
+                        delay = 5 * (2 ** attempt) + random.uniform(0, 1)
+                        utils.logger.warning(
+                            f"[BilibiliClient.get_video_all_comments] Retrying video_id {video_id} in {delay:.2f}s... (Attempt {attempt + 1}/{max_retries})"
+                        )
+                        await asyncio.sleep(delay)
+                    else:
+                        utils.logger.error(
+                            f"[BilibiliClient.get_video_all_comments] Max retries reached for video_id: {video_id}. Skipping comments. Error: {e}"
+                        )
+                        is_end = True
+                        break
+            if not comments_res:
+                break
+
             cursor_info: Dict = comments_res.get("cursor")
+            if not cursor_info:
+                utils.logger.warning(f"[BilibiliClient.get_video_all_comments] Could not find 'cursor' in response for video_id: {video_id}. Skipping.")
+                break
+
             comment_list: List[Dict] = comments_res.get("replies", [])
-            is_end = cursor_info.get("is_end")
-            next_page = cursor_info.get("next")
+            
+            # 检查 is_end 和 next 是否存在
+            if "is_end" not in cursor_info or "next" not in cursor_info:
+                utils.logger.warning(f"[BilibiliClient.get_video_all_comments] 'is_end' or 'next' not in cursor for video_id: {video_id}. Assuming end of comments.")
+                is_end = True
+            else:
+                is_end = cursor_info.get("is_end")
+                next_page = cursor_info.get("next")
+
+            if not isinstance(is_end, bool):
+                utils.logger.warning(f"[BilibiliClient.get_video_all_comments] 'is_end' is not a boolean for video_id: {video_id}. Assuming end of comments.")
+                is_end = True
             if is_fetch_sub_comments:
                 for comment in comment_list:
                     comment_id = comment['rpid']

media_platform/bilibili/config.py

@@ -0,0 +1,34 @@
+# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
+# 1. 不得用于任何商业用途。
+# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
+# 3. 不得进行大规模爬取或对平台造成运营干扰。
+# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
+# 5. 不得用于任何非法或不当的用途。
+#
+# 详细许可条款请参阅项目根目录下的LICENSE文件。
+# 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。
+
+
+from config import *
+
+# 每天爬取视频/帖子的数量控制
+MAX_NOTES_PER_DAY = 1
+
+# Bilibili 平台配置
+BILI_SPECIFIED_ID_LIST = [
+    "BV1d54y1g7db",
+    "BV1Sz4y1U77N",
+    "BV14Q4y1n7jz",
+    # ........................
+]
+START_DAY = "2024-01-01"
+END_DAY = "2024-01-01"
+BILI_SEARCH_MODE = "normal"
+CREATOR_MODE = True
+START_CONTACTS_PAGE = 1
+CRAWLER_MAX_CONTACTS_COUNT_SINGLENOTES = 100
+CRAWLER_MAX_DYNAMICS_COUNT_SINGLENOTES = 50
+BILI_CREATOR_ID_LIST = [
+    "20813884",
+    # ........................
+]