feat: 增加 IP 代理的最新实现

base/base_crawler.py

@@ -1,6 +1,6 @@
 from abc import ABC, abstractmethod
 
-from base.proxy_account_pool import AccountPool
+from proxy.proxy_account_pool import AccountPool
 
 
 class AbstractCrawler(ABC):

main.py

@@ -4,10 +4,10 @@
 
 import config
 import db
-from base import proxy_account_pool
 from media_platform.douyin import DouYinCrawler
 from media_platform.kuaishou import KuaishouCrawler
 from media_platform.xhs import XiaoHongShuCrawler
+from proxy import proxy_account_pool
 
 
 class CrawlerFactory:

media_platform/douyin/core.py

@@ -8,8 +8,8 @@
 
 import config
 from base.base_crawler import AbstractCrawler
-from base.proxy_account_pool import AccountPool
 from models import douyin
+from proxy.proxy_account_pool import AccountPool
 from tools import utils
 from var import crawler_type_var
 

media_platform/kuaishou/core.py

@@ -10,8 +10,8 @@
 
 import config
 from base.base_crawler import AbstractCrawler
-from base.proxy_account_pool import AccountPool
 from models import kuaishou
+from proxy.proxy_account_pool import AccountPool
 from tools import utils
 from var import comment_tasks_var, crawler_type_var
 

media_platform/kuaishou/graphql.py

@@ -1,6 +1,6 @@
 # 快手的数据传输是基于GraphQL实现的
 # 这个类负责获取一些GraphQL的schema
-from typing import  Dict
+from typing import Dict
 
 
 class KuaiShouGraphQL:

media_platform/xhs/core.py

@@ -9,8 +9,8 @@
 
 import config
 from base.base_crawler import AbstractCrawler
-from base.proxy_account_pool import AccountPool
 from models import xiaohongshu as xhs_model
+from proxy.proxy_account_pool import AccountPool
 from tools import utils
 from var import crawler_type_var
 

models/kuaishou.py

@@ -61,6 +61,8 @@ def __str__(self):
 async def update_kuaishou_video(video_item: Dict):
     photo_info: Dict = video_item.get("photo", {})
     video_id = photo_info.get("id")
+    if not video_id:
+        return
     user_info = video_item.get("author", {})
     local_db_item = {
         "video_id": video_id,

proxy/__init__.py

@@ -0,0 +1,4 @@
+# -*- coding: utf-8 -*-
+# @Author  : relakkes@gmail.com
+# @Time    : 2023/12/2 14:37
+# @Desc    :

base/proxy_account_pool.py → proxy/proxy_account_pool.py

@@ -1,3 +1,8 @@
+# -*- coding: utf-8 -*-
+# @Author  : relakkes@gmail.com
+# @Time    : 2023/12/2 11:18
+# @Desc    : IP 和 手机号 一一配对的账号代理池
+
 from typing import List, Optional, Set, Tuple
 
 import config

proxy/proxy_ip_pool.py

@@ -0,0 +1,89 @@
+# -*- coding: utf-8 -*-
+# @Author  : relakkes@gmail.com
+# @Time    : 2023/12/2 13:45
+# @Desc    : ip代理池实现
+import random
+from typing import List
+
+import httpx
+from tenacity import retry, stop_after_attempt, wait_fixed
+
+from tools import utils
+
+from .proxy_ip_provider import IpInfoModel, IpProxy
+
+
+class ProxyIpPool:
+    def __init__(self, ip_pool_count: int, enable_validate_ip: bool) -> None:
+        self.valid_ip_url = "https://httpbin.org/ip"  # 验证 IP 是否有效的地址
+        self.ip_pool_count = ip_pool_count
+        self.enable_validate_ip = enable_validate_ip
+        self.proxy_list: List[IpInfoModel] = []
+
+    async def load_proxies(self) -> None:
+        """
+        从 HTTP 代理商获取 IP 列表
+        :return:
+        """
+        self.proxy_list = await IpProxy.get_proxies(self.ip_pool_count)
+
+    @retry(stop=stop_after_attempt(3), wait=wait_fixed(1))
+    async def is_valid_proxy(self, proxy: IpInfoModel) -> bool:
+        """
+        验证代理IP是否有效
+        :param proxy:
+        :return:
+        """
+        utils.logger.info(f"[ProxyIpPool.is_valid_proxy] testing {proxy.ip} is it valid ")
+        try:
+            httpx_proxy = f"{proxy.protocol}{proxy.ip}:{proxy.port}"
+            proxy_auth = httpx.BasicAuth(proxy.user, proxy.password)
+            async with httpx.AsyncClient(proxies={proxy.protocol: httpx_proxy}, auth=proxy_auth) as client:
+                response = await client.get(self.valid_ip_url)
+            if response.status_code == 200:
+                return True
+            else:
+                return False
+        except Exception as e:
+            utils.logger.info(f"[ProxyIpPool.is_valid_proxy] testing {proxy.ip} err: {e}")
+            raise e
+
+    @retry(stop=stop_after_attempt(3), wait=wait_fixed(1))
+    async def get_proxy(self) -> IpInfoModel:
+        """
+        从代理池中随机提取一个代理IP
+        :return:
+        """
+        if len(self.proxy_list) == 0:
+            await self.reload_proxies()
+
+        proxy = random.choice(self.proxy_list)
+        if self.enable_validate_ip:
+            if not await self.is_valid_proxy(proxy):
+                raise Exception("[ProxyIpPool.get_proxy] current ip invalid and again get it")
+        self.proxy_list.remove(proxy)
+        return proxy
+
+    async def reload_proxies(self):
+        """
+        # 重新加载代理池
+        :return:
+        """
+        self.proxy_list = []
+        await self.load_proxies()
+
+
+async def create_ip_pool(ip_pool_count: int, enable_validate_ip) -> ProxyIpPool:
+    """
+     创建 IP 代理池
+    :param ip_pool_count:
+    :param enable_validate_ip:
+    :return:
+    """
+    pool = ProxyIpPool(ip_pool_count, enable_validate_ip)
+    await pool.load_proxies()
+    return pool
+
+
+if __name__ == '__main__':
+    pass

proxy/proxy_ip_provider.py

@@ -0,0 +1,111 @@
+# -*- coding: utf-8 -*-
+# @Author  : relakkes@gmail.com
+# @Time    : 2023/12/2 11:18
+# @Desc    : 爬虫 IP 获取实现
+# @Url     : 现在实现了极速HTTP的接口，官网地址：https://www.jisuhttp.com/?pl=mAKphQ&plan=ZY&kd=Yang
+
+import asyncio
+import os
+from abc import ABC, abstractmethod
+from typing import Dict, List, Optional
+from urllib.parse import urlencode
+
+import httpx
+from pydantic import BaseModel, Field
+
+from tools import utils
+
+
+class IpGetError(Exception):
+    """ ip get error"""
+
+
+class IpInfoModel(BaseModel):
+    """Unified IP model"""
+    ip: str = Field(title="ip")
+    port: int = Field(title="端口")
+    user: str = Field(title="IP代理认证的用户名")
+    protocol: str = Field(default="https://", title="代理IP的协议")
+    password: str = Field(title="IP代理认证用户的密码")
+    expired_time_ts: Optional[int] = Field(title="IP 过期时间")
+
+
+class ProxyProvider(ABC):
+    @abstractmethod
+    async def get_proxies(self, num: int) -> List[Dict]:
+        """
+        获取 IP 的抽象方法，不同的 HTTP 代理商需要实现该方法
+        :param num: 提取的 IP 数量
+        :return:
+        """
+        pass
+
+
+class JiSuHttpProxy(ProxyProvider):
+    def __init__(self, exract_type: str, key: str, crypto: str, res_type: str, protocol: int, time: int):
+        """
+        极速HTTP 代理IP实现
+        官网地址：https://www.jisuhttp.com/?pl=mAKphQ&plan=ZY&kd=Yang
+        :param exract_type: 提取方式
+        :param key: 提取key值 (到上面链接的官网去注册后获取)
+        :param crypto: 加密签名 (到上面链接的官网去注册后获取)
+        :param res_type: 返回的数据格式：TXT、JSON
+        :param protocol: IP协议：1:HTTP、2:HTTPS、3:SOCKS5
+        :param time: IP使用时长，支持3、5、10、15、30分钟时效
+        """
+        self.exract_type = exract_type
+        self.api_path = "https://api.jisuhttp.com"
+        self.params = {
+            "key": key,
+            "crypto": crypto,
+            "type": res_type,
+            "port": protocol,
+            "time": time,
+            "pw": "1",  # 是否使用账密验证， 1：是，0：否，否表示白名单验证；默认为0
+            "se": "1",  # 返回JSON格式时是否显示IP过期时间， 1：显示，0：不显示；默认为0
+        }
+
+    async def get_proxies(self, num: int) -> List[IpInfoModel]:
+        """
+        :param num:
+        :return:
+        """
+        if self.exract_type == "API":
+            uri = "/fetchips"
+            self.params.update({"num": num})
+            ip_infos = []
+            async with httpx.AsyncClient() as client:
+                url = self.api_path + uri + '?' + urlencode(self.params)
+                utils.logger.info(f"[JiSuHttpProxy] get ip proxy url:{url}")
+                response = await client.get(url, headers={"User-Agent": "MediaCrawler"})
+                res_dict: Dict = response.json()
+                if res_dict.get("code") == 0:
+                    data: List[Dict] = res_dict.get("data")
+                    for ip_item in data:
+                        ip_info_model = IpInfoModel(
+                            ip=ip_item.get("ip"),
+                            port=ip_item.get("port"),
+                            user=ip_item.get("user"),
+                            password=ip_item.get("pass"),
+                            expired_time_ts=utils.get_unix_time_from_time_str(ip_item.get("expire"))
+                        )
+                        ip_infos.append(ip_info_model)
+                else:
+                    raise IpGetError(res_dict.get("msg", "unkown err"))
+            return ip_infos
+        else:
+            pass
+
+
+
+IpProxy = JiSuHttpProxy(
+    key=os.getenv("jisu_key", ""),  # 通过环境变量的方式获取极速HTTPIP提取key值
+    crypto=os.getenv("jisu_crypto", ""),  # 通过环境变量的方式获取极速HTTPIP提取加密签名
+    res_type="json",
+    protocol=2,
+    time=30
+)
+
+if __name__ == '__main__':
+    _ip_infos = asyncio.run(IpProxy.get_proxies(1))
+    print(_ip_infos)

test/test_proxy_ip_pool.py

@@ -0,0 +1,17 @@
+# -*- coding: utf-8 -*-
+# @Author  : relakkes@gmail.com
+# @Time    : 2023/12/2 14:42
+# @Desc    :
+from unittest import IsolatedAsyncioTestCase
+
+from proxy.proxy_ip_pool import create_ip_pool
+from proxy.proxy_ip_provider import IpInfoModel
+
+
+class TestIpPool(IsolatedAsyncioTestCase):
+    async def test_ip_pool(self):
+        pool = await create_ip_pool(ip_pool_count=30, enable_validate_ip=False)
+        for i in range(30):
+            ip_proxy_info: IpInfoModel = await pool.get_proxy()
+            self.assertIsNotNone(ip_proxy_info.ip, msg="验证 ip 是否获取成功")
+            print(ip_proxy_info)

tools/crawler_util.py

@@ -0,0 +1,94 @@
+# -*- coding: utf-8 -*-
+# @Author  : relakkes@gmail.com
+# @Time    : 2023/12/2 12:53
+# @Desc    : 爬虫相关的工具函数
+
+import base64
+import random
+import re
+from io import BytesIO
+from typing import Dict, List, Optional, Tuple
+
+from PIL import Image, ImageDraw
+from playwright.async_api import Cookie, Page
+
+
+async def find_login_qrcode(page: Page, selector: str) -> str:
+    """find login qrcode image from target selector"""
+    try:
+        elements = await page.wait_for_selector(
+            selector=selector,
+        )
+        login_qrcode_img = await elements.get_property("src")  # type: ignore
+        return str(login_qrcode_img)
+
+    except Exception as e:
+        print(e)
+        return ""
+
+
+def show_qrcode(qr_code) -> None:  # type: ignore
+    """parse base64 encode qrcode image and show it"""
+    qr_code = qr_code.split(",")[1]
+    qr_code = base64.b64decode(qr_code)
+    image = Image.open(BytesIO(qr_code))
+
+    # Add a square border around the QR code and display it within the border to improve scanning accuracy.
+    width, height = image.size
+    new_image = Image.new('RGB', (width + 20, height + 20), color=(255, 255, 255))
+    new_image.paste(image, (10, 10))
+    draw = ImageDraw.Draw(new_image)
+    draw.rectangle((0, 0, width + 19, height + 19), outline=(0, 0, 0), width=1)
+    new_image.show()
+
+
+def get_user_agent() -> str:
+    ua_list = [
+        "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/114.0.0.0 Safari/537.36",
+        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.5112.79 Safari/537.36",
+        "Mozilla/5.0 (Windows NT 10.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.0.0 Safari/537.36",
+        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/104.0.0.0 Safari/537.36",
+        "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/103.0.5060.53 Safari/537.36",
+        "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_3) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/99.0.4844.84 Safari/537.36"
+    ]
+    return random.choice(ua_list)
+
+
+def convert_cookies(cookies: Optional[List[Cookie]]) -> Tuple[str, Dict]:
+    if not cookies:
+        return "", {}
+    cookies_str = ";".join([f"{cookie.get('name')}={cookie.get('value')}" for cookie in cookies])
+    cookie_dict = dict()
+    for cookie in cookies:
+        cookie_dict[cookie.get('name')] = cookie.get('value')
+    return cookies_str, cookie_dict
+
+
+def convert_str_cookie_to_dict(cookie_str: str) -> Dict:
+    cookie_dict: Dict[str, str] = dict()
+    if not cookie_str:
+        return cookie_dict
+    for cookie in cookie_str.split(";"):
+        cookie = cookie.strip()
+        if not cookie:
+            continue
+        cookie_list = cookie.split("=")
+        if len(cookie_list) != 2:
+            continue
+        cookie_value = cookie_list[1]
+        if isinstance(cookie_value, list):
+            cookie_value = "".join(cookie_value)
+        cookie_dict[cookie_list[0]] = cookie_value
+    return cookie_dict
+
+
+def match_interact_info_count(count_str: str) -> int:
+    if not count_str:
+        return 0
+
+    match = re.search(r'\d+', count_str)
+    if match:
+        number = match.group()
+        return int(number)
+    else:
+        return 0