通过测试search模式,修复部分运行时的bug,并对能够爬取媒体的平台设置了较长的超时时间

This commit is contained in:
未来可欺
2025-07-30 21:19:56 +08:00
parent a7cc18ec7d
commit 93a1c27fff
5 changed files with 202 additions and 237 deletions
+3 -3
View File
@@ -26,11 +26,11 @@ from .field import *
from .help import *
class DOUYINClient(AbstractApiClient):
class DouYinClient(AbstractApiClient):
def __init__(
self,
timeout=30,
timeout=30, # 若开启爬取媒体选项,抖音的短视频需要更久的超时时间
proxies=None,
*,
headers: Dict,
@@ -314,7 +314,7 @@ class DOUYINClient(AbstractApiClient):
async def get_aweme_media(self, url: str) -> Union[bytes, None]:
async with httpx.AsyncClient(proxies=self.proxies) as client:
response = await client.request("GET", url, timeout=self.timeout)
response = await client.request("GET", url, timeout=self.timeout, follow_redirects=True)
if not response.reason_phrase == "OK":
utils.logger.error(f"[DouYinCrawler.get_aweme_media] request {url} err, res:{response.text}")
return None
+10 -11
View File
@@ -30,7 +30,7 @@ from tools import utils
from tools.cdp_browser import CDPBrowserManager
from var import crawler_type_var, source_keyword_var
from .client import DOUYINClient
from .client import DouYinClient
from .exception import DataFetchError
from .field import PublishTimeType
from .login import DouYinLogin
@@ -38,7 +38,7 @@ from .login import DouYinLogin
class DouYinCrawler(AbstractCrawler):
context_page: Page
dy_client: DOUYINClient
dy_client: DouYinClient
browser_context: BrowserContext
cdp_manager: Optional[CDPBrowserManager]
@@ -233,10 +233,10 @@ class DouYinCrawler(AbstractCrawler):
await douyin_store.update_douyin_aweme(aweme_item=aweme_item)
await self.get_aweme_media(aweme_item=aweme_item)
async def create_douyin_client(self, httpx_proxy: Optional[str]) -> DOUYINClient:
async def create_douyin_client(self, httpx_proxy: Optional[str]) -> DouYinClient:
"""Create douyin client"""
cookie_str, cookie_dict = utils.convert_cookies(await self.browser_context.cookies()) # type: ignore
douyin_client = DOUYINClient(
douyin_client = DouYinClient(
proxies=httpx_proxy,
headers={
"User-Agent": await self.context_page.evaluate("() => navigator.userAgent"),
@@ -385,10 +385,9 @@ class DouYinCrawler(AbstractCrawler):
if not video_download_url:
return
videoNum = 0
for url in video_download_url:
content = await self.xhs_client.get_note_media(url)
if content is None:
continue
extension_file_name = f"{videoNum}.mp4"
videoNum += 1
await douyin_store.update_dy_aweme_image(aweme_id, content, extension_file_name)
content = await self.dy_client.get_aweme_media(video_download_url)
if content is None:
return
extension_file_name = f"{videoNum}.mp4"
videoNum += 1
await douyin_store.update_dy_aweme_video(aweme_id, content, extension_file_name)