Uploading the AI Crawler System: MindSpider

MindSpider/DeepSentimentCrawling/MediaCrawler/store/weibo/__init__.py

@@ -0,0 +1,190 @@
+# 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。
+
+# -*- coding: utf-8 -*-
+# @Author  : relakkes@gmail.com
+# @Time    : 2024/1/14 21:34
+# @Desc    :
+
+import re
+from typing import List
+
+from var import source_keyword_var
+
+from .weibo_store_media import *
+from .weibo_store_impl import *
+
+
+class WeibostoreFactory:
+    STORES = {
+        "csv": WeiboCsvStoreImplement,
+        "db": WeiboDbStoreImplement,
+        "json": WeiboJsonStoreImplement,
+        "sqlite": WeiboSqliteStoreImplement,
+    }
+
+    @staticmethod
+    def create_store() -> AbstractStore:
+        store_class = WeibostoreFactory.STORES.get(config.SAVE_DATA_OPTION)
+        if not store_class:
+            raise ValueError("[WeibotoreFactory.create_store] Invalid save option only supported csv or db or json or sqlite ...")
+        return store_class()
+
+
+async def batch_update_weibo_notes(note_list: List[Dict]):
+    """
+    Batch update weibo notes
+    Args:
+        note_list:
+
+    Returns:
+
+    """
+    if not note_list:
+        return
+    for note_item in note_list:
+        await update_weibo_note(note_item)
+
+
+async def update_weibo_note(note_item: Dict):
+    """
+    Update weibo note
+    Args:
+        note_item:
+
+    Returns:
+
+    """
+    if not note_item:
+        return
+
+    mblog: Dict = note_item.get("mblog")
+    user_info: Dict = mblog.get("user")
+    note_id = mblog.get("id")
+    content_text = mblog.get("text")
+    clean_text = re.sub(r"<.*?>", "", content_text)
+    save_content_item = {
+        # 微博信息
+        "note_id": note_id,
+        "content": clean_text,
+        "create_time": utils.rfc2822_to_timestamp(mblog.get("created_at")),
+        "create_date_time": str(utils.rfc2822_to_china_datetime(mblog.get("created_at"))),
+        "liked_count": str(mblog.get("attitudes_count", 0)),
+        "comments_count": str(mblog.get("comments_count", 0)),
+        "shared_count": str(mblog.get("reposts_count", 0)),
+        "last_modify_ts": utils.get_current_timestamp(),
+        "note_url": f"https://m.weibo.cn/detail/{note_id}",
+        "ip_location": mblog.get("region_name", "").replace("发布于 ", ""),
+
+        # 用户信息
+        "user_id": str(user_info.get("id")),
+        "nickname": user_info.get("screen_name", ""),
+        "gender": user_info.get("gender", ""),
+        "profile_url": user_info.get("profile_url", ""),
+        "avatar": user_info.get("profile_image_url", ""),
+        "source_keyword": source_keyword_var.get(),
+    }
+    utils.logger.info(f"[store.weibo.update_weibo_note] weibo note id:{note_id}, title:{save_content_item.get('content')[:24]} ...")
+    await WeibostoreFactory.create_store().store_content(content_item=save_content_item)
+
+
+async def batch_update_weibo_note_comments(note_id: str, comments: List[Dict]):
+    """
+    Batch update weibo note comments
+    Args:
+        note_id:
+        comments:
+
+    Returns:
+
+    """
+    if not comments:
+        return
+    for comment_item in comments:
+        await update_weibo_note_comment(note_id, comment_item)
+
+
+async def update_weibo_note_comment(note_id: str, comment_item: Dict):
+    """
+    Update weibo note comment
+    Args:
+        note_id: weibo note id
+        comment_item: weibo comment item
+
+    Returns:
+
+    """
+    if not comment_item or not note_id:
+        return
+    comment_id = str(comment_item.get("id"))
+    user_info: Dict = comment_item.get("user")
+    content_text = comment_item.get("text")
+    clean_text = re.sub(r"<.*?>", "", content_text)
+    save_comment_item = {
+        "comment_id": comment_id,
+        "create_time": utils.rfc2822_to_timestamp(comment_item.get("created_at")),
+        "create_date_time": str(utils.rfc2822_to_china_datetime(comment_item.get("created_at"))),
+        "note_id": note_id,
+        "content": clean_text,
+        "sub_comment_count": str(comment_item.get("total_number", 0)),
+        "comment_like_count": str(comment_item.get("like_count", 0)),
+        "last_modify_ts": utils.get_current_timestamp(),
+        "ip_location": comment_item.get("source", "").replace("来自", ""),
+        "parent_comment_id": comment_item.get("rootid", ""),
+
+        # 用户信息
+        "user_id": str(user_info.get("id")),
+        "nickname": user_info.get("screen_name", ""),
+        "gender": user_info.get("gender", ""),
+        "profile_url": user_info.get("profile_url", ""),
+        "avatar": user_info.get("profile_image_url", ""),
+    }
+    utils.logger.info(f"[store.weibo.update_weibo_note_comment] Weibo note comment: {comment_id}, content: {save_comment_item.get('content', '')[:24]} ...")
+    await WeibostoreFactory.create_store().store_comment(comment_item=save_comment_item)
+
+
+async def update_weibo_note_image(picid: str, pic_content, extension_file_name):
+    """
+    Save weibo note image to local
+    Args:
+        picid:
+        pic_content:
+        extension_file_name:
+
+    Returns:
+
+    """
+    await WeiboStoreImage().store_image({"pic_id": picid, "pic_content": pic_content, "extension_file_name": extension_file_name})
+
+
+async def save_creator(user_id: str, user_info: Dict):
+    """
+    Save creator information to local
+    Args:
+        user_id:
+        user_info:
+
+    Returns:
+
+    """
+    local_db_item = {
+        'user_id': user_id,
+        'nickname': user_info.get('screen_name'),
+        'gender': '女' if user_info.get('gender') == "f" else '男',
+        'avatar': user_info.get('avatar_hd'),
+        'desc': user_info.get('description'),
+        'ip_location': user_info.get("source", "").replace("来自", ""),
+        'follows': user_info.get('follow_count', ''),
+        'fans': user_info.get('followers_count', ''),
+        'tag_list': '',
+        "last_modify_ts": utils.get_current_timestamp(),
+    }
+    utils.logger.info(f"[store.weibo.save_creator] creator:{local_db_item}")
+    await WeibostoreFactory.create_store().store_creator(local_db_item)

MindSpider/DeepSentimentCrawling/MediaCrawler/store/weibo/weibo_store_impl.py

@@ -0,0 +1,326 @@
+# 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。  
+
+
+# -*- coding: utf-8 -*-
+# @Author  : relakkes@gmail.com
+# @Time    : 2024/1/14 21:35
+# @Desc    : 微博存储实现类
+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 WeiboCsvStoreImplement(AbstractStore):
+    csv_store_path: str = "data/weibo"
+    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/bilibili/search_comments_20240114.csv ...
+
+        """
+
+        return f"{self.csv_store_path}/{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:
+            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):
+        """
+        Weibo 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):
+        """
+        Weibo 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):
+        """
+        Weibo creator CSV storage implementation
+        Args:
+            creator:
+
+        Returns:
+
+        """
+        await self.save_data_to_csv(save_item=creator, store_type="creators")
+
+
+class WeiboDbStoreImplement(AbstractStore):
+
+    async def store_content(self, content_item: Dict):
+        """
+        Weibo content DB storage implementation
+        Args:
+            content_item: content item dict
+
+        Returns:
+
+        """
+
+        from .weibo_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):
+        """
+        Weibo content DB storage implementation
+        Args:
+            comment_item: comment item dict
+
+        Returns:
+
+        """
+        from .weibo_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):
+        """
+        Weibo creator DB storage implementation
+        Args:
+            creator:
+
+        Returns:
+
+        """
+
+        from .weibo_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 WeiboJsonStoreImplement(AbstractStore):
+    json_store_path: str = "data/weibo/json"
+    words_store_path: str = "data/weibo/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 implementation
+        Args:
+            comment_item:
+
+        Returns:
+
+        """
+        await self.save_data_to_json(comment_item, "comments")
+
+    async def store_creator(self, creator: Dict):
+        """
+        creator JSON storage implementation
+        Args:
+            creator:
+
+        Returns:
+
+        """
+        await self.save_data_to_json(creator, "creators")
+
+
+class WeiboSqliteStoreImplement(AbstractStore):
+    async def store_content(self, content_item: Dict):
+        """
+        Weibo content SQLite storage implementation
+        Args:
+            content_item: content item dict
+
+        Returns:
+
+        """
+
+        from .weibo_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):
+        """
+        Weibo comment SQLite storage implementation
+        Args:
+            comment_item: comment item dict
+
+        Returns:
+
+        """
+        from .weibo_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):
+        """
+        Weibo creator SQLite storage implementation
+        Args:
+            creator:
+
+        Returns:
+
+        """
+
+        from .weibo_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)

MindSpider/DeepSentimentCrawling/MediaCrawler/store/weibo/weibo_store_media.py

@@ -0,0 +1,68 @@
+# 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。
+
+# -*- coding: utf-8 -*-
+# @Author  : Erm
+# @Time    : 2024/4/9 17:35
+# @Desc    : 微博媒体保存
+import pathlib
+from typing import Dict
+
+import aiofiles
+
+from base.base_crawler import AbstractStoreImage, AbstractStoreVideo
+from tools import utils
+
+
+class WeiboStoreImage(AbstractStoreImage):
+    image_store_path: str = "data/weibo/images"
+
+    async def store_image(self, image_content_item: Dict):
+        """
+        store content
+        
+        Args:
+            image_content_item:
+
+        Returns:
+
+        """
+        await self.save_image(image_content_item.get("pic_id"), image_content_item.get("pic_content"), image_content_item.get("extension_file_name"))
+
+    def make_save_file_name(self, picid: str, extension_file_name: str) -> str:
+        """
+        make save file name by store type
+        
+        Args:
+            picid: image id
+            extension_file_name: video filename with extension
+
+        Returns:
+
+        """
+        return f"{self.image_store_path}/{picid}.{extension_file_name}"
+
+    async def save_image(self, picid: str, pic_content: str, extension_file_name="jpg"):
+        """
+        save image to local
+        
+        Args:
+            picid: image id
+            pic_content: image content
+            extension_file_name: image filename with extension
+
+        Returns:
+
+        """
+        pathlib.Path(self.image_store_path).mkdir(parents=True, exist_ok=True)
+        save_file_name = self.make_save_file_name(picid, extension_file_name)
+        async with aiofiles.open(save_file_name, 'wb') as f:
+            await f.write(pic_content)
+            utils.logger.info(f"[WeiboImageStoreImplement.save_image] save image {save_file_name} success ...")

MindSpider/DeepSentimentCrawling/MediaCrawler/store/weibo/weibo_store_sql.py

@@ -0,0 +1,160 @@
+# 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。  
+
+
+# -*- coding: utf-8 -*-
+# @Author  : relakkes@gmail.com
+# @Time    : 2024/4/6 15:30
+# @Desc    : sql接口集合
+
+from typing import Dict, List, Union
+
+from async_db import AsyncMysqlDB
+from async_sqlite_db import AsyncSqliteDB
+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: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
+    sql: str = f"select * from weibo_note 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: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
+    last_row_id: int = await async_db_conn.item_to_table("weibo_note", 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: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
+    effect_row: int = await async_db_conn.update_table("weibo_note", 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: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
+    sql: str = f"select * from weibo_note_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: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
+    last_row_id: int = await async_db_conn.item_to_table("weibo_note_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: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
+    effect_row: int = await async_db_conn.update_table("weibo_note_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: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
+    sql: str = f"select * from weibo_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: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
+    last_row_id: int = await async_db_conn.item_to_table("weibo_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: Union[AsyncMysqlDB, AsyncSqliteDB] = media_crawler_db_var.get()
+    effect_row: int = await async_db_conn.update_table("weibo_creator", creator_item, "user_id", user_id)
+    return effect_row