jiazhizhong/MediaCrawler
1
0
Fork 0
mirror of https://github.com/NanmiCoder/MediaCrawler.git synced 2026-06-01 07:27:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

fix: weibo get note image fixed

Browse Source
This commit is contained in:
程序员阿江(Relakkes)
2025-12-26 00:47:20 +08:00
parent 11500ef57a
commit ff1b681311
1 changed files with 10 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
media_platform/weibo/core.py
View File

@@ -276,11 +276,18 @@ class WeiboCrawler(AbstractCrawler):
utils.logger.info(f"[WeiboCrawler.get_note_images] Crawling image mode is not enabled") utils.logger.info(f"[WeiboCrawler.get_note_images] Crawling image mode is not enabled")
return return
pics: Dict = mblog.get("pics") pics: List = mblog.get("pics")
if not pics: if not pics:
return return
for pic in pics: for pic in pics:
if isinstance(pic, str):
url = pic
pid = url.split("/")[-1].split(".")[0]
elif isinstance(pic, dict):
url = pic.get("url") url = pic.get("url")
pid = pic.get("pid", "")
else:
continue
if not url: if not url:
continue continue
content = await self.wb_client.get_note_image(url) content = await self.wb_client.get_note_image(url)
@@ -288,7 +295,7 @@ class WeiboCrawler(AbstractCrawler):
utils.logger.info(f"[WeiboCrawler.get_note_images] Sleeping for {config.CRAWLER_MAX_SLEEP_SEC} seconds after fetching image") utils.logger.info(f"[WeiboCrawler.get_note_images] Sleeping for {config.CRAWLER_MAX_SLEEP_SEC} seconds after fetching image")
if content != None: if content != None:
extension_file_name = url.split(".")[-1] extension_file_name = url.split(".")[-1]
await weibo_store.update_weibo_note_image(pic["pid"], content, extension_file_name) await weibo_store.update_weibo_note_image(pid, content, extension_file_name)
async def get_creators_and_notes(self) -> None: async def get_creators_and_notes(self) -> None:
""" """