feat: 百度贴吧架子 & 登录done

store/tieba/__init__.py

@@ -0,0 +1,91 @@
+# -*- coding: utf-8 -*-
+from typing import List
+
+from . import tieba_store_impl
+from .tieba_store_impl import *
+
+
+class TieBaStoreFactory:
+    STORES = {
+        "csv": TieBaCsvStoreImplement,
+        "db": TieBaDbStoreImplement,
+        "json": TieBaJsonStoreImplement
+    }
+
+    @staticmethod
+    def create_store() -> AbstractStore:
+        store_class = TieBaStoreFactory.STORES.get(config.SAVE_DATA_OPTION)
+        if not store_class:
+            raise ValueError(
+                "[TieBaStoreFactory.create_store] Invalid save option only supported csv or db or json ...")
+        return store_class()
+
+
+async def update_tieba_note(note_item: Dict):
+    note_id = note_item.get("note_id")
+    user_info = note_item.get("user", {})
+    interact_info = note_item.get("interact_info", {})
+    tag_list: List[Dict] = note_item.get("tag_list", [])
+
+    local_db_item = {
+        "note_id": note_id,
+        "type": note_item.get("type"),
+        "title": note_item.get("title") or note_item.get("desc", "")[:255],
+        "desc": note_item.get("desc", ""),
+        "time": note_item.get("time"),
+        "last_update_time": note_item.get("last_update_time", 0),
+        "user_id": user_info.get("user_id"),
+        "nickname": user_info.get("nickname"),
+        "avatar": user_info.get("avatar"),
+        "liked_count": interact_info.get("liked_count"),
+        "collected_count": interact_info.get("collected_count"),
+        "comment_count": interact_info.get("comment_count"),
+        "share_count": interact_info.get("share_count"),
+        "ip_location": note_item.get("ip_location", ""),
+
+        "tag_list": ','.join([tag.get('name', '') for tag in tag_list if tag.get('type') == 'topic']),
+        "last_modify_ts": utils.get_current_timestamp(),
+        # todo: add note_url
+        "note_url": ""
+    }
+    utils.logger.info(f"[store.tieba.update_tieba_note] tieba note: {local_db_item}")
+    await TieBaStoreFactory.create_store().store_content(local_db_item)
+
+
+async def batch_update_tieba_note_comments(note_id: str, comments: List[Dict]):
+    if not comments:
+        return
+    for comment_item in comments:
+        await update_tieba_note_comment(note_id, comment_item)
+
+
+async def update_tieba_note_comment(note_id: str, comment_item: Dict):
+    """
+    Update tieba note comment
+    Args:
+        note_id:
+        comment_item:
+
+    Returns:
+
+    """
+    user_info = comment_item.get("user_info", {})
+    comment_id = comment_item.get("id")
+    comment_pictures = [item.get("url_default", "") for item in comment_item.get("pictures", [])]
+    target_comment = comment_item.get("target_comment", {})
+    local_db_item = {
+        "comment_id": comment_id,
+        "create_time": comment_item.get("create_time"),
+        "ip_location": comment_item.get("ip_location"),
+        "note_id": note_id,
+        "content": comment_item.get("content"),
+        "user_id": user_info.get("user_id"),
+        "nickname": user_info.get("nickname"),
+        "avatar": user_info.get("image"),
+        "sub_comment_count": comment_item.get("sub_comment_count", 0),
+        "pictures": ",".join(comment_pictures),
+        "parent_comment_id": target_comment.get("id", 0),
+        "last_modify_ts": utils.get_current_timestamp(),
+    }
+    utils.logger.info(f"[store.tieba.update_tieba_note_comment] tieba note comment:{local_db_item}")
+    await TieBaStoreFactory.create_store().store_comment(local_db_item)

store/tieba/tieba_store_impl.py

@@ -0,0 +1,244 @@
+# -*- coding: utf-8 -*-
+import asyncio
+import csv
+import json
+import os
+import pathlib
+from typing import Dict
+
+import aiofiles
+
+import config
+from base.base_crawler import AbstractStore
+from tools import utils, words
+from var import crawler_type_var
+
+
+def calculate_number_of_files(file_store_path: str) -> int:
+    """计算数据保存文件的前部分排序数字，支持每次运行代码不写到同一个文件中
+    Args:
+        file_store_path;
+    Returns:
+        file nums
+    """
+    if not os.path.exists(file_store_path):
+        return 1
+    try:
+        return max([int(file_name.split("_")[0])for file_name in os.listdir(file_store_path)])+1
+    except ValueError:
+        return 1
+
+
+class TieBaCsvStoreImplement(AbstractStore):
+    csv_store_path: str = "data/tieba"
+    file_count:int=calculate_number_of_files(csv_store_path)
+
+    def make_save_file_name(self, store_type: str) -> str:
+        """
+        make save file name by store type
+        Args:
+            store_type: contents or comments
+
+        Returns: eg: data/tieba/search_comments_20240114.csv ...
+
+        """
+        return f"{self.csv_store_path}/{self.file_count}_{crawler_type_var.get()}_{store_type}_{utils.get_current_date()}.csv"
+
+    async def save_data_to_csv(self, save_item: Dict, store_type: str):
+        """
+        Below is a simple way to save it in CSV format.
+        Args:
+            save_item:  save content dict info
+            store_type: Save type contains content and comments（contents | comments）
+
+        Returns: no returns
+
+        """
+        pathlib.Path(self.csv_store_path).mkdir(parents=True, exist_ok=True)
+        save_file_name = self.make_save_file_name(store_type=store_type)
+        async with aiofiles.open(save_file_name, mode='a+', encoding="utf-8-sig", newline="") as f:
+            f.fileno()
+            writer = csv.writer(f)
+            if await f.tell() == 0:
+                await writer.writerow(save_item.keys())
+            await writer.writerow(save_item.values())
+
+    async def store_content(self, content_item: Dict):
+        """
+        Xiaohongshu content CSV storage implementation
+        Args:
+            content_item: note item dict
+
+        Returns:
+
+        """
+        await self.save_data_to_csv(save_item=content_item, store_type="contents")
+
+    async def store_comment(self, comment_item: Dict):
+        """
+        Xiaohongshu comment CSV storage implementation
+        Args:
+            comment_item: comment item dict
+
+        Returns:
+
+        """
+        await self.save_data_to_csv(save_item=comment_item, store_type="comments")
+
+    async def store_creator(self, creator: Dict):
+        """
+        Xiaohongshu content CSV storage implementation
+        Args:
+            creator: creator dict
+
+        Returns:
+
+        """
+        await self.save_data_to_csv(save_item=creator, store_type="creator")
+
+
+class TieBaDbStoreImplement(AbstractStore):
+    async def store_content(self, content_item: Dict):
+        """
+        Xiaohongshu content DB storage implementation
+        Args:
+            content_item: content item dict
+
+        Returns:
+
+        """
+        from .tieba_store_sql import (add_new_content,
+                                      query_content_by_content_id,
+                                      update_content_by_content_id)
+        note_id = content_item.get("note_id")
+        note_detail: Dict = await query_content_by_content_id(content_id=note_id)
+        if not note_detail:
+            content_item["add_ts"] = utils.get_current_timestamp()
+            await add_new_content(content_item)
+        else:
+            await update_content_by_content_id(note_id, content_item=content_item)
+
+    async def store_comment(self, comment_item: Dict):
+        """
+        Xiaohongshu content DB storage implementation
+        Args:
+            comment_item: comment item dict
+
+        Returns:
+
+        """
+        from .tieba_store_sql import (add_new_comment,
+                                      query_comment_by_comment_id,
+                                      update_comment_by_comment_id)
+        comment_id = comment_item.get("comment_id")
+        comment_detail: Dict = await query_comment_by_comment_id(comment_id=comment_id)
+        if not comment_detail:
+            comment_item["add_ts"] = utils.get_current_timestamp()
+            await add_new_comment(comment_item)
+        else:
+            await update_comment_by_comment_id(comment_id, comment_item=comment_item)
+
+    async def store_creator(self, creator: Dict):
+        """
+        Xiaohongshu content DB storage implementation
+        Args:
+            creator: creator dict
+
+        Returns:
+
+        """
+        from .tieba_store_sql import (add_new_creator,
+                                      query_creator_by_user_id,
+                                      update_creator_by_user_id)
+        user_id = creator.get("user_id")
+        user_detail: Dict = await query_creator_by_user_id(user_id)
+        if not user_detail:
+            creator["add_ts"] = utils.get_current_timestamp()
+            await add_new_creator(creator)
+        else:
+            await update_creator_by_user_id(user_id, creator)
+
+
+class TieBaJsonStoreImplement(AbstractStore):
+    json_store_path: str = "data/tieba/json"
+    words_store_path: str = "data/tieba/words"
+    lock = asyncio.Lock()
+    file_count:int=calculate_number_of_files(json_store_path)
+    WordCloud = words.AsyncWordCloudGenerator()
+
+    def make_save_file_name(self, store_type: str) -> (str,str):
+        """
+        make save file name by store type
+        Args:
+            store_type: Save type contains content and comments（contents | comments）
+
+        Returns:
+
+        """
+
+        return (
+            f"{self.json_store_path}/{crawler_type_var.get()}_{store_type}_{utils.get_current_date()}.json",
+            f"{self.words_store_path}/{crawler_type_var.get()}_{store_type}_{utils.get_current_date()}"
+        )
+
+    async def save_data_to_json(self, save_item: Dict, store_type: str):
+        """
+        Below is a simple way to save it in json format.
+        Args:
+            save_item: save content dict info
+            store_type: Save type contains content and comments（contents | comments）
+
+        Returns:
+
+        """
+        pathlib.Path(self.json_store_path).mkdir(parents=True, exist_ok=True)
+        pathlib.Path(self.words_store_path).mkdir(parents=True, exist_ok=True)
+        save_file_name,words_file_name_prefix = self.make_save_file_name(store_type=store_type)
+        save_data = []
+
+        async with self.lock:
+            if os.path.exists(save_file_name):
+                async with aiofiles.open(save_file_name, 'r', encoding='utf-8') as file:
+                    save_data = json.loads(await file.read())
+
+            save_data.append(save_item)
+            async with aiofiles.open(save_file_name, 'w', encoding='utf-8') as file:
+                await file.write(json.dumps(save_data, ensure_ascii=False))
+
+            if config.ENABLE_GET_COMMENTS and config.ENABLE_GET_WORDCLOUD:
+                try:
+                    await self.WordCloud.generate_word_frequency_and_cloud(save_data, words_file_name_prefix)
+                except:
+                    pass
+    async def store_content(self, content_item: Dict):
+        """
+        content JSON storage implementation
+        Args:
+            content_item:
+
+        Returns:
+
+        """
+        await self.save_data_to_json(content_item, "contents")
+
+    async def store_comment(self, comment_item: Dict):
+        """
+        comment JSON storage implementatio
+        Args:
+            comment_item:
+
+        Returns:
+
+        """
+        await self.save_data_to_json(comment_item, "comments")
+
+    async def store_creator(self, creator: Dict):
+        """
+        Xiaohongshu content JSON storage implementation
+        Args:
+            creator: creator dict
+
+        Returns:
+
+        """
+        await self.save_data_to_json(creator, "creator")

store/tieba/tieba_store_sql.py

@@ -0,0 +1,144 @@
+# -*- coding: utf-8 -*-
+from typing import Dict, List
+
+from db import AsyncMysqlDB
+from var import media_crawler_db_var
+
+
+async def query_content_by_content_id(content_id: str) -> Dict:
+    """
+    查询一条内容记录（xhs的帖子 ｜ 抖音的视频 ｜ 微博 ｜ 快手视频 ...）
+    Args:
+        content_id:
+
+    Returns:
+
+    """
+    async_db_conn: AsyncMysqlDB = media_crawler_db_var.get()
+    sql: str = f"select * from baidu_tieba where note_id = '{content_id}'"
+    rows: List[Dict] = await async_db_conn.query(sql)
+    if len(rows) > 0:
+        return rows[0]
+    return dict()
+
+
+async def add_new_content(content_item: Dict) -> int:
+    """
+    新增一条内容记录（xhs的帖子 ｜ 抖音的视频 ｜ 微博 ｜ 快手视频 ...）
+    Args:
+        content_item:
+
+    Returns:
+
+    """
+    async_db_conn: AsyncMysqlDB = media_crawler_db_var.get()
+    last_row_id: int = await async_db_conn.item_to_table("baidu_tieba", content_item)
+    return last_row_id
+
+
+async def update_content_by_content_id(content_id: str, content_item: Dict) -> int:
+    """
+    更新一条记录（xhs的帖子 ｜ 抖音的视频 ｜ 微博 ｜ 快手视频 ...）
+    Args:
+        content_id:
+        content_item:
+
+    Returns:
+
+    """
+    async_db_conn: AsyncMysqlDB = media_crawler_db_var.get()
+    effect_row: int = await async_db_conn.update_table("baidu_tieba", content_item, "note_id", content_id)
+    return effect_row
+
+
+
+async def query_comment_by_comment_id(comment_id: str) -> Dict:
+    """
+    查询一条评论内容
+    Args:
+        comment_id:
+
+    Returns:
+
+    """
+    async_db_conn: AsyncMysqlDB = media_crawler_db_var.get()
+    sql: str = f"select * from baidu_tieba_comment where comment_id = '{comment_id}'"
+    rows: List[Dict] = await async_db_conn.query(sql)
+    if len(rows) > 0:
+        return rows[0]
+    return dict()
+
+
+async def add_new_comment(comment_item: Dict) -> int:
+    """
+    新增一条评论记录
+    Args:
+        comment_item:
+
+    Returns:
+
+    """
+    async_db_conn: AsyncMysqlDB = media_crawler_db_var.get()
+    last_row_id: int = await async_db_conn.item_to_table("baidu_tieba_comment", comment_item)
+    return last_row_id
+
+
+async def update_comment_by_comment_id(comment_id: str, comment_item: Dict) -> int:
+    """
+    更新增一条评论记录
+    Args:
+        comment_id:
+        comment_item:
+
+    Returns:
+
+    """
+    async_db_conn: AsyncMysqlDB = media_crawler_db_var.get()
+    effect_row: int = await async_db_conn.update_table("baidu_tieba_comment", comment_item, "comment_id", comment_id)
+    return effect_row
+
+
+async def query_creator_by_user_id(user_id: str) -> Dict:
+    """
+    查询一条创作者记录
+    Args:
+        user_id:
+
+    Returns:
+
+    """
+    async_db_conn: AsyncMysqlDB = media_crawler_db_var.get()
+    sql: str = f"select * from baidu_tieba_creator where user_id = '{user_id}'"
+    rows: List[Dict] = await async_db_conn.query(sql)
+    if len(rows) > 0:
+        return rows[0]
+    return dict()
+
+
+async def add_new_creator(creator_item: Dict) -> int:
+    """
+    新增一条创作者信息
+    Args:
+        creator_item:
+
+    Returns:
+
+    """
+    async_db_conn: AsyncMysqlDB = media_crawler_db_var.get()
+    last_row_id: int = await async_db_conn.item_to_table("baidu_tieba_creator", creator_item)
+    return last_row_id
+
+
+async def update_creator_by_user_id(user_id: str, creator_item: Dict) -> int:
+    """
+    更新一条创作者信息
+    Args:
+        user_id:
+        creator_item:
+
+    Returns:
+
+    """
+    async_db_conn: AsyncMysqlDB = media_crawler_db_var.get()
+    effect_row: int = await async_db_conn.update_table("baidu_tieba_creator", creator_item, "user_id", user_id)
+    return effect_row