jiazhizhong/MediaCrawler
1
0
Fork 0
mirror of https://github.com/NanmiCoder/MediaCrawler.git synced 2026-06-08 19:07:33 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: ip proxy expired check

Browse Source
This commit is contained in:
程序员阿江(Relakkes)
2025-11-25 12:39:10 +08:00
parent 1da347cbf8
commit 6eef02d08c
16 changed files with 241 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
media_platform/bilibili/client.py
View File

@@ -24,7 +24,7 @@
import asyncio
import json
import random
from typing import Any, Callable, Dict, List, Optional, Tuple, Union
from typing import TYPE_CHECKING, Any, Callable, Dict, List, Optional, Tuple, Union
from urllib.parse import urlencode
import httpx
@@ -32,14 +32,18 @@ from playwright.async_api import BrowserContext, Page
import config
from base.base_crawler import AbstractApiClient
from proxy.proxy_mixin import ProxyRefreshMixin
from tools import utils
if TYPE_CHECKING:
from proxy.proxy_ip_pool import ProxyIpPool
from .exception import DataFetchError
from .field import CommentOrderType, SearchOrderType
from .help import BilibiliSign
class BilibiliClient(AbstractApiClient):
class BilibiliClient(AbstractApiClient, ProxyRefreshMixin):
def __init__(
self,
@@ -49,6 +53,7 @@ class BilibiliClient(AbstractApiClient):
headers: Dict[str, str],
playwright_page: Page,
cookie_dict: Dict[str, str],
proxy_ip_pool: Optional["ProxyIpPool"] = None,
):
self.proxy = proxy
self.timeout = timeout
@@ -56,8 +61,13 @@ class BilibiliClient(AbstractApiClient):
self._host = "https://api.bilibili.com"
self.playwright_page = playwright_page
self.cookie_dict = cookie_dict
# 初始化代理池（来自 ProxyRefreshMixin）
self.init_proxy_pool(proxy_ip_pool)
async def request(self, method, url, **kwargs) -> Any:
# 每次请求前检测代理是否过期
await self._refresh_proxy_if_expired()
async with httpx.AsyncClient(proxy=self.proxy) as client:
response = await client.request(method, url, timeout=self.timeout, **kwargs)
try:

6
media_platform/bilibili/core.py
View File

@@ -64,12 +64,13 @@ class BilibiliCrawler(AbstractCrawler):
self.index_url = "https://www.bilibili.com"
self.user_agent = utils.get_user_agent()
self.cdp_manager = None
self.ip_proxy_pool = None # 代理IP池，用于代理自动刷新
async def start(self):
playwright_proxy_format, httpx_proxy_format = None, None
if config.ENABLE_IP_PROXY:
ip_proxy_pool = await create_ip_pool(config.IP_PROXY_POOL_COUNT, enable_validate_ip=True)
ip_proxy_info: IpInfoModel = await ip_proxy_pool.get_proxy()
self.ip_proxy_pool = await create_ip_pool(config.IP_PROXY_POOL_COUNT, enable_validate_ip=True)
ip_proxy_info: IpInfoModel = await self.ip_proxy_pool.get_proxy()
playwright_proxy_format, httpx_proxy_format = utils.format_proxy_info(ip_proxy_info)
async with async_playwright() as playwright:
@@ -473,6 +474,7 @@ class BilibiliCrawler(AbstractCrawler):
},
playwright_page=self.context_page,
cookie_dict=cookie_dict,
proxy_ip_pool=self.ip_proxy_pool, # 传递代理池用于自动刷新
)
return bilibili_client_obj

14
media_platform/douyin/client.py
View File

@@ -21,21 +21,25 @@ import asyncio
import copy
import json
import urllib.parse
from typing import Any, Callable, Dict, Union, Optional
from typing import TYPE_CHECKING, Any, Callable, Dict, Union, Optional
import httpx
from playwright.async_api import BrowserContext
from base.base_crawler import AbstractApiClient
from proxy.proxy_mixin import ProxyRefreshMixin
from tools import utils
from var import request_keyword_var
if TYPE_CHECKING:
from proxy.proxy_ip_pool import ProxyIpPool
from .exception import *
from .field import *
from .help import *
class DouYinClient(AbstractApiClient):
class DouYinClient(AbstractApiClient, ProxyRefreshMixin):
def __init__(
self,
@@ -45,6 +49,7 @@ class DouYinClient(AbstractApiClient):
headers: Dict,
playwright_page: Optional[Page],
cookie_dict: Dict,
proxy_ip_pool: Optional["ProxyIpPool"] = None,
):
self.proxy = proxy
self.timeout = timeout
@@ -52,6 +57,8 @@ class DouYinClient(AbstractApiClient):
self._host = "https://www.douyin.com"
self.playwright_page = playwright_page
self.cookie_dict = cookie_dict
# 初始化代理池（来自 ProxyRefreshMixin）
self.init_proxy_pool(proxy_ip_pool)
async def __process_req_params(
self,
@@ -106,6 +113,9 @@ class DouYinClient(AbstractApiClient):
params["a_bogus"] = a_bogus
async def request(self, method, url, **kwargs):
# 每次请求前检测代理是否过期
await self._refresh_proxy_if_expired()
async with httpx.AsyncClient(proxy=self.proxy) as client:
response = await client.request(method, url, timeout=self.timeout, **kwargs)
try:

6
media_platform/douyin/core.py
View File

@@ -55,12 +55,13 @@ class DouYinCrawler(AbstractCrawler):
def __init__(self) -> None:
self.index_url = "https://www.douyin.com"
self.cdp_manager = None
self.ip_proxy_pool = None # 代理IP池，用于代理自动刷新
async def start(self) -> None:
playwright_proxy_format, httpx_proxy_format = None, None
if config.ENABLE_IP_PROXY:
ip_proxy_pool = await create_ip_pool(config.IP_PROXY_POOL_COUNT, enable_validate_ip=True)
ip_proxy_info: IpInfoModel = await ip_proxy_pool.get_proxy()
self.ip_proxy_pool = await create_ip_pool(config.IP_PROXY_POOL_COUNT, enable_validate_ip=True)
ip_proxy_info: IpInfoModel = await self.ip_proxy_pool.get_proxy()
playwright_proxy_format, httpx_proxy_format = utils.format_proxy_info(ip_proxy_info)
async with async_playwright() as playwright:
@@ -305,6 +306,7 @@ class DouYinCrawler(AbstractCrawler):
},
playwright_page=self.context_page,
cookie_dict=cookie_dict,
proxy_ip_pool=self.ip_proxy_pool, # 传递代理池用于自动刷新
)
return douyin_client

14
media_platform/kuaishou/client.py
View File

@@ -21,7 +21,7 @@
# -*- coding: utf-8 -*-
import asyncio
import json
from typing import Any, Callable, Dict, List, Optional
from typing import TYPE_CHECKING, Any, Callable, Dict, List, Optional
from urllib.parse import urlencode
import httpx
@@ -29,13 +29,17 @@ from playwright.async_api import BrowserContext, Page
import config
from base.base_crawler import AbstractApiClient
from proxy.proxy_mixin import ProxyRefreshMixin
from tools import utils
if TYPE_CHECKING:
from proxy.proxy_ip_pool import ProxyIpPool
from .exception import DataFetchError
from .graphql import KuaiShouGraphQL
class KuaiShouClient(AbstractApiClient):
class KuaiShouClient(AbstractApiClient, ProxyRefreshMixin):
def __init__(
self,
timeout=10,
@@ -44,6 +48,7 @@ class KuaiShouClient(AbstractApiClient):
headers: Dict[str, str],
playwright_page: Page,
cookie_dict: Dict[str, str],
proxy_ip_pool: Optional["ProxyIpPool"] = None,
):
self.proxy = proxy
self.timeout = timeout
@@ -52,8 +57,13 @@ class KuaiShouClient(AbstractApiClient):
self.playwright_page = playwright_page
self.cookie_dict = cookie_dict
self.graphql = KuaiShouGraphQL()
# 初始化代理池（来自 ProxyRefreshMixin）
self.init_proxy_pool(proxy_ip_pool)
async def request(self, method, url, **kwargs) -> Any:
# 每次请求前检测代理是否过期
await self._refresh_proxy_if_expired()
async with httpx.AsyncClient(proxy=self.proxy) as client:
response = await client.request(method, url, timeout=self.timeout, **kwargs)
data: Dict = response.json()

6
media_platform/kuaishou/core.py
View File

@@ -58,14 +58,15 @@ class KuaishouCrawler(AbstractCrawler):
self.index_url = "https://www.kuaishou.com"
self.user_agent = utils.get_user_agent()
self.cdp_manager = None
self.ip_proxy_pool = None # 代理IP池，用于代理自动刷新
async def start(self):
playwright_proxy_format, httpx_proxy_format = None, None
if config.ENABLE_IP_PROXY:
ip_proxy_pool = await create_ip_pool(
self.ip_proxy_pool = await create_ip_pool(
config.IP_PROXY_POOL_COUNT, enable_validate_ip=True
)
ip_proxy_info: IpInfoModel = await ip_proxy_pool.get_proxy()
ip_proxy_info: IpInfoModel = await self.ip_proxy_pool.get_proxy()
playwright_proxy_format, httpx_proxy_format = utils.format_proxy_info(
ip_proxy_info
)
@@ -317,6 +318,7 @@ class KuaishouCrawler(AbstractCrawler):
},
playwright_page=self.context_page,
cookie_dict=cookie_dict,
proxy_ip_pool=self.ip_proxy_pool, # 传递代理池用于自动刷新
)
return ks_client_obj

21
media_platform/tieba/client.py
View File

@@ -89,6 +89,24 @@ class BaiduTieBaClient(AbstractApiClient):
)
return response
async def _refresh_proxy_if_expired(self) -> None:
"""
检测代理是否过期，如果过期则自动刷新
"""
if self.ip_pool is None:
return
if self.ip_pool.is_current_proxy_expired():
utils.logger.info(
"[BaiduTieBaClient._refresh_proxy_if_expired] Proxy expired, refreshing..."
)
new_proxy = await self.ip_pool.get_or_refresh_proxy()
# 更新代理URL
_, self.default_ip_proxy = utils.format_proxy_info(new_proxy)
utils.logger.info(
f"[BaiduTieBaClient._refresh_proxy_if_expired] New proxy: {new_proxy.ip}:{new_proxy.port}"
)
@retry(stop=stop_after_attempt(3), wait=wait_fixed(1))
async def request(self, method, url, return_ori_content=False, proxy=None, **kwargs) -> Union[str, Any]:
"""
@@ -103,6 +121,9 @@ class BaiduTieBaClient(AbstractApiClient):
Returns:
"""
# 每次请求前检测代理是否过期
await self._refresh_proxy_if_expired()
actual_proxy = proxy if proxy else self.default_ip_proxy
# 在线程池中执行同步的requests请求

14
media_platform/weibo/client.py
View File

@@ -26,7 +26,7 @@ import asyncio
import copy
import json
import re
from typing import Callable, Dict, List, Optional, Union
from typing import TYPE_CHECKING, Callable, Dict, List, Optional, Union
from urllib.parse import parse_qs, unquote, urlencode
import httpx
@@ -35,13 +35,17 @@ from playwright.async_api import BrowserContext, Page
from tenacity import retry, stop_after_attempt, wait_fixed
import config
from proxy.proxy_mixin import ProxyRefreshMixin
from tools import utils
if TYPE_CHECKING:
from proxy.proxy_ip_pool import ProxyIpPool
from .exception import DataFetchError
from .field import SearchType
class WeiboClient:
class WeiboClient(ProxyRefreshMixin):
def __init__(
self,
@@ -51,6 +55,7 @@ class WeiboClient:
headers: Dict[str, str],
playwright_page: Page,
cookie_dict: Dict[str, str],
proxy_ip_pool: Optional["ProxyIpPool"] = None,
):
self.proxy = proxy
self.timeout = timeout
@@ -59,9 +64,14 @@ class WeiboClient:
self.playwright_page = playwright_page
self.cookie_dict = cookie_dict
self._image_agent_host = "https://i1.wp.com/"
# 初始化代理池（来自 ProxyRefreshMixin）
self.init_proxy_pool(proxy_ip_pool)
@retry(stop=stop_after_attempt(5), wait=wait_fixed(3))
async def request(self, method, url, **kwargs) -> Union[Response, Dict]:
# 每次请求前检测代理是否过期
await self._refresh_proxy_if_expired()
enable_return_response = kwargs.pop("return_response", False)
async with httpx.AsyncClient(proxy=self.proxy) as client:
response = await client.request(method, url, timeout=self.timeout, **kwargs)

6
media_platform/weibo/core.py
View File

@@ -63,12 +63,13 @@ class WeiboCrawler(AbstractCrawler):
self.user_agent = utils.get_user_agent()
self.mobile_user_agent = utils.get_mobile_user_agent()
self.cdp_manager = None
self.ip_proxy_pool = None # 代理IP池，用于代理自动刷新
async def start(self):
playwright_proxy_format, httpx_proxy_format = None, None
if config.ENABLE_IP_PROXY:
ip_proxy_pool = await create_ip_pool(config.IP_PROXY_POOL_COUNT, enable_validate_ip=True)
ip_proxy_info: IpInfoModel = await ip_proxy_pool.get_proxy()
self.ip_proxy_pool = await create_ip_pool(config.IP_PROXY_POOL_COUNT, enable_validate_ip=True)
ip_proxy_info: IpInfoModel = await self.ip_proxy_pool.get_proxy()
playwright_proxy_format, httpx_proxy_format = utils.format_proxy_info(ip_proxy_info)
async with async_playwright() as playwright:
@@ -334,6 +335,7 @@ class WeiboCrawler(AbstractCrawler):
},
playwright_page=self.context_page,
cookie_dict=cookie_dict,
proxy_ip_pool=self.ip_proxy_pool, # 传递代理池用于自动刷新
)
return weibo_client_obj

16
media_platform/xhs/client.py
View File

@@ -20,7 +20,7 @@
import asyncio
import json
import time
from typing import Any, Callable, Dict, List, Optional, Union
from typing import TYPE_CHECKING, Any, Callable, Dict, List, Optional, Union
from urllib.parse import urlencode, urlparse, parse_qs
@@ -31,8 +31,11 @@ from xhshow import Xhshow
import config
from base.base_crawler import AbstractApiClient
from proxy.proxy_mixin import ProxyRefreshMixin
from tools import utils
if TYPE_CHECKING:
from proxy.proxy_ip_pool import ProxyIpPool
from .exception import DataFetchError, IPBlockError
from .field import SearchNoteType, SearchSortType
@@ -40,7 +43,7 @@ from .help import get_search_id, sign
from .extractor import XiaoHongShuExtractor
class XiaoHongShuClient(AbstractApiClient):
class XiaoHongShuClient(AbstractApiClient, ProxyRefreshMixin):
def __init__(
self,
@@ -50,6 +53,7 @@ class XiaoHongShuClient(AbstractApiClient):
headers: Dict[str, str],
playwright_page: Page,
cookie_dict: Dict[str, str],
proxy_ip_pool: Optional["ProxyIpPool"] = None,
):
self.proxy = proxy
self.timeout = timeout
@@ -65,6 +69,8 @@ class XiaoHongShuClient(AbstractApiClient):
self._extractor = XiaoHongShuExtractor()
# 初始化 xhshow 客户端用于签名生成
self._xhshow_client = Xhshow()
# 初始化代理池（来自 ProxyRefreshMixin）
self.init_proxy_pool(proxy_ip_pool)
async def _pre_headers(self, url: str, params: Optional[Dict] = None, payload: Optional[Dict] = None) -> Dict:
"""请求头参数签名
@@ -132,6 +138,9 @@ class XiaoHongShuClient(AbstractApiClient):
Returns:
"""
# 每次请求前检测代理是否过期
await self._refresh_proxy_if_expired()
# return response.text
return_response = kwargs.pop("return_response", False)
async with httpx.AsyncClient(proxy=self.proxy) as client:
@@ -201,6 +210,9 @@ class XiaoHongShuClient(AbstractApiClient):
)
async def get_note_media(self, url: str) -> Union[bytes, None]:
# 请求前检测代理是否过期
await self._refresh_proxy_if_expired()
async with httpx.AsyncClient(proxy=self.proxy) as client:
try:
response = await client.request("GET", url, timeout=self.timeout)

6
media_platform/xhs/core.py
View File

@@ -60,12 +60,13 @@ class XiaoHongShuCrawler(AbstractCrawler):
# self.user_agent = utils.get_user_agent()
self.user_agent = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/126.0.0.0 Safari/537.36"
self.cdp_manager = None
self.ip_proxy_pool = None # 代理IP池，用于代理自动刷新
async def start(self) -> None:
playwright_proxy_format, httpx_proxy_format = None, None
if config.ENABLE_IP_PROXY:
ip_proxy_pool = await create_ip_pool(config.IP_PROXY_POOL_COUNT, enable_validate_ip=True)
ip_proxy_info: IpInfoModel = await ip_proxy_pool.get_proxy()
self.ip_proxy_pool = await create_ip_pool(config.IP_PROXY_POOL_COUNT, enable_validate_ip=True)
ip_proxy_info: IpInfoModel = await self.ip_proxy_pool.get_proxy()
playwright_proxy_format, httpx_proxy_format = utils.format_proxy_info(ip_proxy_info)
async with async_playwright() as playwright:
@@ -380,6 +381,7 @@ class XiaoHongShuCrawler(AbstractCrawler):
},
playwright_page=self.context_page,
cookie_dict=cookie_dict,
proxy_ip_pool=self.ip_proxy_pool, # 传递代理池用于自动刷新
)
return xhs_client_obj

14
media_platform/zhihu/client.py
View File

@@ -20,7 +20,7 @@
# -*- coding: utf-8 -*-
import asyncio
import json
from typing import Any, Callable, Dict, List, Optional, Union
from typing import TYPE_CHECKING, Any, Callable, Dict, List, Optional, Union
from urllib.parse import urlencode
import httpx
@@ -32,14 +32,18 @@ import config
from base.base_crawler import AbstractApiClient
from constant import zhihu as zhihu_constant
from model.m_zhihu import ZhihuComment, ZhihuContent, ZhihuCreator
from proxy.proxy_mixin import ProxyRefreshMixin
from tools import utils
if TYPE_CHECKING:
from proxy.proxy_ip_pool import ProxyIpPool
from .exception import DataFetchError, ForbiddenError
from .field import SearchSort, SearchTime, SearchType
from .help import ZhihuExtractor, sign
class ZhiHuClient(AbstractApiClient):
class ZhiHuClient(AbstractApiClient, ProxyRefreshMixin):
def __init__(
self,
@@ -49,12 +53,15 @@ class ZhiHuClient(AbstractApiClient):
headers: Dict[str, str],
playwright_page: Page,
cookie_dict: Dict[str, str],
proxy_ip_pool: Optional["ProxyIpPool"] = None,
):
self.proxy = proxy
self.timeout = timeout
self.default_headers = headers
self.cookie_dict = cookie_dict
self._extractor = ZhihuExtractor()
# 初始化代理池（来自 ProxyRefreshMixin）
self.init_proxy_pool(proxy_ip_pool)
async def _pre_headers(self, url: str) -> Dict:
"""
@@ -85,6 +92,9 @@ class ZhiHuClient(AbstractApiClient):
Returns:
"""
# 每次请求前检测代理是否过期
await self._refresh_proxy_if_expired()
# return response.text
return_response = kwargs.pop('return_response', False)

6
media_platform/zhihu/core.py
View File

@@ -61,6 +61,7 @@ class ZhihuCrawler(AbstractCrawler):
self.user_agent = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/128.0.0.0 Safari/537.36"
self._extractor = ZhihuExtractor()
self.cdp_manager = None
self.ip_proxy_pool = None # 代理IP池，用于代理自动刷新
async def start(self) -> None:
"""
@@ -70,10 +71,10 @@ class ZhihuCrawler(AbstractCrawler):
"""
playwright_proxy_format, httpx_proxy_format = None, None
if config.ENABLE_IP_PROXY:
ip_proxy_pool = await create_ip_pool(
self.ip_proxy_pool = await create_ip_pool(
config.IP_PROXY_POOL_COUNT, enable_validate_ip=True
)
ip_proxy_info: IpInfoModel = await ip_proxy_pool.get_proxy()
ip_proxy_info: IpInfoModel = await self.ip_proxy_pool.get_proxy()
playwright_proxy_format, httpx_proxy_format = utils.format_proxy_info(
ip_proxy_info
)
@@ -411,6 +412,7 @@ class ZhihuCrawler(AbstractCrawler):
},
playwright_page=self.context_page,
cookie_dict=cookie_dict,
proxy_ip_pool=self.ip_proxy_pool, # 传递代理池用于自动刷新
)
return zhihu_client_obj