injectlib/MediaCrawler
1
0
Fork 0
mirror of https://github.com/NanmiCoder/MediaCrawler.git synced 2025-11-25 03:15:17 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #699 from 2513502304/main

Browse Source 
添加了对媒体资源服务器的异常处理，参见 issue #691
This commit is contained in:
程序员阿江-Relakkes
2025-08-05 16:11:03 +08:00
committed by GitHub
parent b9d30bbabb 81f2dbe4ab
commit e4e0f659e0
8 changed files with 50 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files

15
media_platform/bilibili/client.py
View File

@@ -202,12 +202,17 @@ class BilibiliClient(AbstractApiClient):
async def get_video_media(self, url: str) -> Union[bytes, None]:
async with httpx.AsyncClient(proxy=self.proxy) as client:
response = await client.request("GET", url, timeout=self.timeout, headers=self.headers)
if not response.reason_phrase == "OK":
utils.logger.error(f"[BilibiliClient.get_video_media] request {url} err, res:{response.text}")
try:
response = await client.request("GET", url, timeout=self.timeout, headers=self.headers)
response.raise_for_status()
if not response.reason_phrase == "OK":
utils.logger.error(f"[BilibiliClient.get_video_media] request {url} err, res:{response.text}")
return None
else:
return response.content
except httpx.HTTPStatusError as exc: # some wrong when call httpx.request method, such as connection error, client error or server error
utils.logger.error(f"[BilibiliClient.get_video_media] {exc}")
return None
else:
return response.content
async def get_video_comments(
self,

1
media_platform/bilibili/core.py
View File

@@ -544,6 +544,7 @@ class BilibiliCrawler(AbstractCrawler):
return
content = await self.bili_client.get_video_media(video_url)
await asyncio.sleep(random.random())
if content is None:
return
extension_file_name = f"video.mp4"

19
media_platform/douyin/client.py
View File

@@ -30,7 +30,7 @@ class DouYinClient(AbstractApiClient):
def __init__(
self,
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
timeout=60, # 若开启爬取媒体选项，抖音的短视频需要更久的超时时间
proxy=None,
*,
headers: Dict,
@@ -305,7 +305,7 @@ class DouYinClient(AbstractApiClient):
posts_has_more = aweme_post_res.get("has_more", 0)
max_cursor = aweme_post_res.get("max_cursor")
aweme_list = aweme_post_res.get("aweme_list") if aweme_post_res.get("aweme_list") else []
utils.logger.info(f"[DouYinCrawler.get_all_user_aweme_posts] get sec_user_id:{sec_user_id} video len : {len(aweme_list)}")
utils.logger.info(f"[DouYinClient.get_all_user_aweme_posts] get sec_user_id:{sec_user_id} video len : {len(aweme_list)}")
if callback:
await callback(aweme_list)
result.extend(aweme_list)
@@ -313,9 +313,14 @@ class DouYinClient(AbstractApiClient):
async def get_aweme_media(self, url: str) -> Union[bytes, None]:
async with httpx.AsyncClient(proxy=self.proxy) as client:
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}")
try:
response = await client.request("GET", url, timeout=self.timeout, follow_redirects=True)
response.raise_for_status()
if not response.reason_phrase == "OK":
utils.logger.error(f"[DouYinClient.get_aweme_media] request {url} err, res:{response.text}")
return None
else:
return response.content
except httpx.HTTPStatusError as exc: # some wrong when call httpx.request method, such as connection error, client error or server error
utils.logger.error(f"[DouYinClient.get_aweme_media] {exc}")
return None
else:
return response.content

2
media_platform/douyin/core.py
View File

@@ -362,6 +362,7 @@ class DouYinCrawler(AbstractCrawler):
if not url:
continue
content = await self.dy_client.get_aweme_media(url)
await asyncio.sleep(random.random())
if content is None:
continue
extension_file_name = f"{picNum:>03d}.jpeg"
@@ -385,6 +386,7 @@ class DouYinCrawler(AbstractCrawler):
if not video_download_url:
return
content = await self.dy_client.get_aweme_media(video_download_url)
await asyncio.sleep(random.random())
if content is None:
return
extension_file_name = f"video.mp4"

17
media_platform/weibo/client.py
View File

@@ -35,7 +35,7 @@ class WeiboClient:
def __init__(
self,
timeout=30, # 若开启爬取媒体选项，weibo 的图片需要更久的超时时间
timeout=60, # 若开启爬取媒体选项，weibo 的图片需要更久的超时时间
proxy=None,
*,
headers: Dict[str, str],
@@ -248,12 +248,17 @@ class WeiboClient:
final_uri = (f"{self._image_agent_host}"
f"{image_url}")
async with httpx.AsyncClient(proxy=self.proxy) as client:
response = await client.request("GET", final_uri, timeout=self.timeout)
if not response.reason_phrase == "OK":
utils.logger.error(f"[WeiboClient.get_note_image] request {final_uri} err, res:{response.text}")
try:
response = await client.request("GET", final_uri, timeout=self.timeout)
response.raise_for_status()
if not response.reason_phrase == "OK":
utils.logger.error(f"[WeiboClient.get_note_image] request {final_uri} err, res:{response.text}")
return None
else:
return response.content
except httpx.HTTPStatusError as exc: # some wrong when call httpx.request method, such as connection error, client error or server error
utils.logger.error(f"[DouYinClient.get_aweme_media] {exc}")
return None
else:
return response.content
async def get_creator_container_info(self, creator_id: str) -> Dict:
"""

1
media_platform/weibo/core.py
View File

@@ -250,6 +250,7 @@ class WeiboCrawler(AbstractCrawler):
if not url:
continue
content = await self.wb_client.get_note_image(url)
await asyncio.sleep(random.random())
if content != None:
extension_file_name = url.split(".")[-1]
await weibo_store.update_weibo_note_image(pic["pid"], content, extension_file_name)

17
media_platform/xhs/client.py
View File

@@ -32,7 +32,7 @@ class XiaoHongShuClient(AbstractApiClient):
def __init__(
self,
timeout=30, # 若开启爬取媒体选项，xhs 的长视频需要更久的超时时间
timeout=60, # 若开启爬取媒体选项，xhs 的长视频需要更久的超时时间
proxy=None,
*,
headers: Dict[str, str],
@@ -152,12 +152,17 @@ class XiaoHongShuClient(AbstractApiClient):
async def get_note_media(self, url: str) -> Union[bytes, None]:
async with httpx.AsyncClient(proxy=self.proxy) as client:
response = await client.request("GET", url, timeout=self.timeout)
if not response.reason_phrase == "OK":
utils.logger.error(f"[XiaoHongShuClient.get_note_media] request {url} err, res:{response.text}")
try:
response = await client.request("GET", url, timeout=self.timeout)
response.raise_for_status()
if not response.reason_phrase == "OK":
utils.logger.error(f"[XiaoHongShuClient.get_note_media] request {url} err, res:{response.text}")
return None
else:
return response.content
except httpx.HTTPStatusError as exc: # some wrong when call httpx.request method, such as connection error, client error or server error
utils.logger.error(f"[DouYinClient.get_aweme_media] {exc}")
return None
else:
return response.content
async def pong(self) -> bool:
"""

2
media_platform/xhs/core.py
View File

@@ -453,6 +453,7 @@ class XiaoHongShuCrawler(AbstractCrawler):
if not url:
continue
content = await self.xhs_client.get_note_media(url)
await asyncio.sleep(random.random())
if content is None:
continue
extension_file_name = f"{picNum}.jpg"
@@ -476,6 +477,7 @@ class XiaoHongShuCrawler(AbstractCrawler):
videoNum = 0
for url in videos:
content = await self.xhs_client.get_note_media(url)
await asyncio.sleep(random.random())
if content is None:
continue
extension_file_name = f"{videoNum}.mp4"