refactor: 优化代码

base/base_crawler.py

@@ -1,17 +1,19 @@
 from abc import ABC, abstractmethod
 
+from base.proxy_account_pool import AccountPool
+
 
 class AbstractCrawler(ABC):
     @abstractmethod
-    def init_config(self, **kwargs):
+    def init_config(self, platform: str, login_type: str, account_pool: AccountPool):
         pass
 
     @abstractmethod
     async def start(self):
         pass
 
     @abstractmethod
-    async def search_posts(self):
+    async def search(self):
         pass
 
 

base/proxy_account_pool.py

@@ -1,4 +1,4 @@
-from typing import Tuple, Optional, List, Set
+from typing import List, Optional, Set, Tuple
 
 import config
 

config/__init__.py

@@ -1,3 +1,3 @@
-from .base_config import *
 from .account_config import *
+from .base_config import *
 from .db_config import *

config/base_config.py

@@ -19,8 +19,8 @@
 # save user data dir
 USER_DATA_DIR = "%s_user_data_dir"  # %s will be replaced by platform name
 
-# max page num
-MAX_PAGE_NUM = 20
+# crawler max notes count
+CRAWLER_MAX_NOTES_COUNT = 20
 
 # max concurrency num
 MAX_CONCURRENCY_NUM = 10

db.py

@@ -1,8 +1,6 @@
-from tortoise import Tortoise
-from tortoise import run_async
+from tortoise import Tortoise, run_async
 
 from config.db_config import *
-
 from tools import utils
 
 

main.py

@@ -1,9 +1,9 @@
-import sys
-import asyncio
 import argparse
+import asyncio
+import sys
 
-import db
 import config
+import db
 from base import proxy_account_pool
 from media_platform.douyin import DouYinCrawler
 from media_platform.xhs import XiaoHongShuCrawler
@@ -17,14 +17,16 @@ def create_crawler(platform: str):
         elif platform == "dy":
             return DouYinCrawler()
         else:
-            raise ValueError("Invalid Media Platform Currently only supported xhs or douyin ...")
+            raise ValueError("Invalid Media Platform Currently only supported xhs or dy ...")
 
 
 async def main():
     # define command line params ...
     parser = argparse.ArgumentParser(description='Media crawler program.')
-    parser.add_argument('--platform', type=str, help='Media platform select (xhs|dy)...', default=config.PLATFORM)
-    parser.add_argument('--lt', type=str, help='Login type (qrcode | phone | cookie)', default=config.LOGIN_TYPE)
+    parser.add_argument('--platform', type=str, help='Media platform select (xhs|dy)', choices=["xhs", "dy"],
+                        default=config.PLATFORM)
+    parser.add_argument('--lt', type=str, help='Login type (qrcode | phone | cookie)',
+                        choices=["qrcode", "phone", "cookie"], default=config.LOGIN_TYPE)
 
     # init account pool
     account_pool = proxy_account_pool.create_account_pool()
@@ -34,16 +36,18 @@ async def main():
         await db.init_db()
 
     args = parser.parse_args()
-    crawler = CrawlerFactory().create_crawler(platform=args.platform)
+    crawler = CrawlerFactory.create_crawler(platform=args.platform)
     crawler.init_config(
-        command_args=args,
+        platform=args.platform,
+        login_type=args.lt,
         account_pool=account_pool
     )
     await crawler.start()
 
 
 if __name__ == '__main__':
     try:
-        asyncio.run(main())
+        # asyncio.run(main())
+        asyncio.get_event_loop().run_until_complete(main())
     except KeyboardInterrupt:
         sys.exit()

media_platform/douyin/client.py

@@ -1,17 +1,17 @@
-import copy
 import asyncio
-from typing import Optional, Dict, Callable
+import copy
+import urllib.parse
+from typing import Callable, Dict, Optional
 
-import httpx
 import execjs
-import urllib.parse
-from playwright.async_api import Page
-from playwright.async_api import BrowserContext
+import httpx
+from playwright.async_api import BrowserContext, Page
 
-from .field import *
-from .exception import *
 from tools import utils
 
+from .exception import *
+from .field import *
+
 
 class DOUYINClient:
     def __init__(

media_platform/douyin/core.py

@@ -1,38 +1,38 @@
-import os
 import asyncio
+import os
 from asyncio import Task
-from argparse import Namespace
-from typing import Optional, List, Dict, Tuple
+from typing import Dict, List, Optional, Tuple
 
-from playwright.async_api import async_playwright
-from playwright.async_api import BrowserType
-from playwright.async_api import BrowserContext
-from playwright.async_api import Page
+from playwright.async_api import (BrowserContext, BrowserType, Page,
+                                  async_playwright)
 
 import config
+from base.base_crawler import AbstractCrawler
+from base.proxy_account_pool import AccountPool
+from models import douyin
 from tools import utils
+
 from .client import DOUYINClient
 from .exception import DataFetchError
 from .login import DouYinLogin
-from base.base_crawler import AbstractCrawler
-from base.proxy_account_pool import AccountPool
-from models import douyin
 
 
 class DouYinCrawler(AbstractCrawler):
+    platform: str
+    login_type: str
+    context_page: Page
     dy_client: DOUYINClient
+    account_pool: AccountPool
+    browser_context: BrowserContext
 
     def __init__(self) -> None:
-        self.browser_context: Optional[BrowserContext] = None  # type: ignore
-        self.context_page: Optional[Page] = None  # type: ignore
         self.user_agent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/109.0.0.0 Safari/537.36"  # fixed
         self.index_url = "https://www.douyin.com"
-        self.command_args: Optional[Namespace] = None  # type: ignore
-        self.account_pool: Optional[AccountPool] = None  # type: ignore
 
-    def init_config(self, **kwargs):
-        for key, value in kwargs.items():
-            setattr(self, key, value)
+    def init_config(self, platform: str, login_type: str, account_pool: AccountPool) -> None:
+        self.platform = platform
+        self.login_type = login_type
+        self.account_pool = account_pool
 
     async def start(self) -> None:
         account_phone, playwright_proxy, httpx_proxy = self.create_proxy_info()
@@ -53,7 +53,7 @@ async def start(self) -> None:
             self.dy_client = await self.create_douyin_client(httpx_proxy)
             if not await self.dy_client.ping(browser_context=self.browser_context):
                 login_obj = DouYinLogin(
-                    login_type=self.command_args.lt,  # type: ignore
+                    login_type=self.login_type,
                     login_phone=account_phone,
                     browser_context=self.browser_context,
                     context_page=self.context_page,
@@ -63,25 +63,25 @@ async def start(self) -> None:
                 await self.dy_client.update_cookies(browser_context=self.browser_context)
 
             # search_posts
-            await self.search_posts()
+            await self.search()
 
             utils.logger.info("Douyin Crawler finished ...")
 
-    async def search_posts(self) -> None:
+    async def search(self) -> None:
         utils.logger.info("Begin search douyin keywords")
         for keyword in config.KEYWORDS.split(","):
             utils.logger.info(f"Current keyword: {keyword}")
             aweme_list: List[str] = []
-            max_note_len = config.MAX_PAGE_NUM
+            dy_limite_count = 10  # douyin fixed limit page 10
             page = 0
-            while max_note_len > 0:
+            while (page + 1) * dy_limite_count <= config.CRAWLER_MAX_NOTES_COUNT:
                 try:
-                    posts_res = await self.dy_client.search_info_by_keyword(keyword=keyword, offset=page * 10)
+                    posts_res = await self.dy_client.search_info_by_keyword(keyword=keyword,
+                                                                            offset=page * dy_limite_count)
                 except DataFetchError:
                     utils.logger.error(f"search douyin keyword: {keyword} failed")
                     break
                 page += 1
-                max_note_len -= 10
                 for post_item in posts_res.get("data"):
                     try:
                         aweme_info: Dict = post_item.get("aweme_info") or \
@@ -93,15 +93,15 @@ async def search_posts(self) -> None:
             utils.logger.info(f"keyword:{keyword}, aweme_list:{aweme_list}")
             await self.batch_get_note_comments(aweme_list)
 
-    async def batch_get_note_comments(self, aweme_list: List[str]):
+    async def batch_get_note_comments(self, aweme_list: List[str]) -> None:
         task_list: List[Task] = []
-        _semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
+        semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
         for aweme_id in aweme_list:
-            task = asyncio.create_task(self.get_comments(aweme_id, _semaphore), name=aweme_id)
+            task = asyncio.create_task(self.get_comments(aweme_id, semaphore), name=aweme_id)
             task_list.append(task)
         await asyncio.wait(task_list)
 
-    async def get_comments(self, aweme_id: str, semaphore: "asyncio.Semaphore"):
+    async def get_comments(self, aweme_id: str, semaphore: asyncio.Semaphore) -> None:
         async with semaphore:
             try:
                 await self.dy_client.get_aweme_all_comments(
@@ -155,7 +155,7 @@ async def launch_browser(
         """Launch browser and create browser context"""
         if config.SAVE_LOGIN_STATE:
             user_data_dir = os.path.join(os.getcwd(), "browser_data",
-                                         config.USER_DATA_DIR % self.command_args.platform)  # type: ignore
+                                         config.USER_DATA_DIR % self.platform)  # type: ignore
             browser_context = await chromium.launch_persistent_context(
                 user_data_dir=user_data_dir,
                 accept_downloads=True,
@@ -173,7 +173,7 @@ async def launch_browser(
             )
             return browser_context
 
-    async def close(self):
+    async def close(self) -> None:
         """Close browser context"""
         await self.browser_context.close()
         utils.logger.info("Browser context closed ...")

media_platform/douyin/login.py

@@ -1,22 +1,17 @@
-import sys
 import asyncio
 import functools
+import sys
 from typing import Optional
 
 import aioredis
-from tenacity import (
-    retry,
-    stop_after_attempt,
-    wait_fixed,
-    retry_if_result,
-    RetryError
-)
-from playwright.async_api import Page, TimeoutError as PlaywrightTimeoutError
-from playwright.async_api import BrowserContext
+from playwright.async_api import BrowserContext, Page
+from playwright.async_api import TimeoutError as PlaywrightTimeoutError
+from tenacity import (RetryError, retry, retry_if_result, stop_after_attempt,
+                      wait_fixed)
 
 import config
-from tools import utils
 from base.base_crawler import AbstractLogin
+from tools import utils
 
 
 class DouYinLogin(AbstractLogin):

media_platform/xhs/client.py

@@ -1,16 +1,16 @@
-import json
 import asyncio
-from typing import Optional, Dict
+import json
+from typing import Dict, Optional
 
 import httpx
-from playwright.async_api import Page
-from playwright.async_api import BrowserContext
+from playwright.async_api import BrowserContext, Page
 
-from .help import sign, get_search_id
-from .field import SearchSortType, SearchNoteType
-from .exception import DataFetchError, IPBlockError
 from tools import utils
 
+from .exception import DataFetchError, IPBlockError
+from .field import SearchNoteType, SearchSortType
+from .help import get_search_id, sign
+
 
 class XHSClient:
     def __init__(