feat: xhs笔记详情更新

This commit is contained in:
Relakkes
2024-07-25 00:44:46 +08:00
parent 678b358e2e
commit 573ca9a659
6 changed files with 67 additions and 36 deletions

View File

@@ -27,7 +27,8 @@ class XiaoHongShuCrawler(AbstractCrawler):
def __init__(self) -> None:
self.index_url = "https://www.xiaohongshu.com"
self.user_agent = utils.get_user_agent()
# 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"
async def start(self) -> None:
playwright_proxy_format, httpx_proxy_format = None, None
@@ -110,18 +111,23 @@ class XiaoHongShuCrawler(AbstractCrawler):
sort=SearchSortType(config.SORT_TYPE) if config.SORT_TYPE != '' else SearchSortType.GENERAL,
)
utils.logger.info(f"[XiaoHongShuCrawler.search] Search notes res:{notes_res}")
if(not notes_res or not notes_res.get('has_more', False)):
if not notes_res or not notes_res.get('has_more', False):
utils.logger.info("No more content!")
break
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
task_list = [
self.get_note_detail(post_item.get("id"), semaphore)
self.get_note_detail(
note_id=post_item.get("id"),
xsec_source=post_item.get("xsec_source"),
xsec_token=post_item.get("xsec_token"),
semaphore=semaphore
)
for post_item in notes_res.get("items", {})
if post_item.get('model_type') not in ('rec_query', 'hot_query')
]
note_details = await asyncio.gather(*task_list)
for note_detail in note_details:
if note_detail is not None:
if note_detail:
await xhs_store.update_xhs_note(note_detail)
await self.get_notice_media(note_detail)
note_id_list.append(note_detail.get("note_id"))
@@ -157,32 +163,42 @@ class XiaoHongShuCrawler(AbstractCrawler):
"""
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
task_list = [
self.get_note_detail(post_item.get("note_id"), semaphore) for post_item in note_list
self.get_note_detail(
note_id=post_item.get("id"),
xsec_source=post_item.get("xsec_source"),
xsec_token=post_item.get("xsec_token"),
semaphore=semaphore
)
for post_item in note_list
]
note_details = await asyncio.gather(*task_list)
for note_detail in note_details:
if note_detail is not None:
if note_detail:
await xhs_store.update_xhs_note(note_detail)
async def get_specified_notes(self):
"""Get the information and comments of the specified post"""
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
task_list = [
self.get_note_detail(note_id=note_id, semaphore=semaphore) for note_id in config.XHS_SPECIFIED_ID_LIST
]
note_details = await asyncio.gather(*task_list)
for note_detail in note_details:
if note_detail is not None:
await xhs_store.update_xhs_note(note_detail)
await self.get_notice_media(note_detail)
await self.batch_get_note_comments(config.XHS_SPECIFIED_ID_LIST)
# todo 指定帖子爬取暂时失效xhs更新了帖子详情的请求参数需要携带xsec_token目前发现该参数只能在搜索场景下获取到
raise Exception(
"指定帖子爬取暂时失效xhs更新了帖子详情的请求参数需要携带xsec_token目前发现只能在搜索场景下获取到")
# semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
# task_list = [
# self.get_note_detail(note_id=note_id, xsec_token="", semaphore=semaphore) for note_id in config.XHS_SPECIFIED_ID_LIST
# ]
# note_details = await asyncio.gather(*task_list)
# for note_detail in note_details:
# if note_detail is not None:
# await xhs_store.update_xhs_note(note_detail)
# await self.get_notice_media(note_detail)
# await self.batch_get_note_comments(config.XHS_SPECIFIED_ID_LIST)
async def get_note_detail(self, note_id: str, semaphore: asyncio.Semaphore) -> Optional[Dict]:
async def get_note_detail(self, note_id: str, xsec_source: str, xsec_token: str, semaphore: asyncio.Semaphore) -> \
Optional[Dict]:
"""Get note detail"""
async with semaphore:
try:
return await self.xhs_client.get_note_by_id(note_id)
return await self.xhs_client.get_note_by_id(note_id, xsec_source, xsec_token)
except DataFetchError as ex:
utils.logger.error(f"[XiaoHongShuCrawler.get_note_detail] Get note detail error: {ex}")
return None