fatsand/xhs_crawler
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: xhs笔记详情更新

Browse Source
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
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
config/base_config.py
View File

@ -40,7 +40,7 @@ START_PAGE = 1
CRAWLER_MAX_NOTES_COUNT = 20
# 并发爬虫数量控制
MAX_CONCURRENCY_NUM = 4
MAX_CONCURRENCY_NUM = 1
# 是否开启爬图片模式, 默认不开启爬图片
ENABLE_GET_IMAGES = False

25
media_platform/xhs/client.py
View File

@ -198,27 +198,34 @@ class XiaoHongShuClient(AbstractApiClient):
}
return await self.post(uri, data)
async def get_note_by_id(self, note_id: str) -> Dict:
async def get_note_by_id(self, note_id: str, xsec_source: str, xsec_token: str) -> Dict:
"""
获取笔记详情API
Args:
note_id:笔记ID
xsec_source: 渠道来源
xsec_token: 搜索关键字之后返回的比较列表中返回的token
Returns:
"""
if xsec_source == "":
xsec_source = "pc_search"
data = {
"source_note_id": note_id,
"image_formats": ["jpg", "webp", "avif"],
"extra": {"need_body_topic": 1},
"xsec_source": "pc_feed",
"xsec_source": xsec_source,
"xsec_token": xsec_token
}
uri = "/api/sns/web/v1/feed"
res = await self.post(uri, data)
if res and res.get("items"):
res_dict: Dict = res["items"][0]["note_card"]
return res_dict
utils.logger.error(f"[XiaoHongShuClient.get_note_by_id] get note empty and res:{res}")
# 爬取频繁了可能会出现有的笔记能有结果有的没有
utils.logger.error(f"[XiaoHongShuClient.get_note_by_id] get note id:{note_id} empty and res:{res}")
return dict()
async def get_note_comments(self, note_id: str, cursor: str = "") -> Dict:
@ -306,7 +313,8 @@ class XiaoHongShuClient(AbstractApiClient):
"""
if not config.ENABLE_GET_SUB_COMMENTS:
utils.logger.info(f"[XiaoHongShuCrawler.get_comments_all_sub_comments] Crawling sub_comment mode is not enabled")
utils.logger.info(
f"[XiaoHongShuCrawler.get_comments_all_sub_comments] Crawling sub_comment mode is not enabled")
return []
result = []
@ -398,17 +406,20 @@ class XiaoHongShuClient(AbstractApiClient):
while notes_has_more:
notes_res = await self.get_notes_by_creator(user_id, notes_cursor)
if not notes_res:
utils.logger.error(f"[XiaoHongShuClient.get_notes_by_creator] The current creator may have been banned by xhs, so they cannot access the data.")
utils.logger.error(
f"[XiaoHongShuClient.get_notes_by_creator] The current creator may have been banned by xhs, so they cannot access the data.")
break
notes_has_more = notes_res.get("has_more", False)
notes_cursor = notes_res.get("cursor", "")
if "notes" not in notes_res:
utils.logger.info(f"[XiaoHongShuClient.get_all_notes_by_creator] No 'notes' key found in response: {notes_res}")
utils.logger.info(
f"[XiaoHongShuClient.get_all_notes_by_creator] No 'notes' key found in response: {notes_res}")
break
notes = notes_res["notes"]
utils.logger.info(f"[XiaoHongShuClient.get_all_notes_by_creator] got user_id:{user_id} notes len : {len(notes)}")
utils.logger.info(
f"[XiaoHongShuClient.get_all_notes_by_creator] got user_id:{user_id} notes len : {len(notes)}")
if callback:
await callback(notes)
await asyncio.sleep(crawl_interval)

52
media_platform/xhs/core.py
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

10
media_platform/xhs/help.py
View File

@ -10,19 +10,19 @@ def sign(a1="", b1="", x_s="", x_t=""):
takes in a URI (uniform resource identifier), an optional data dictionary, and an optional ctime parameter. It returns a dictionary containing two keys: "x-s" and "x-t".
"""
common = {
"s0": 5, # getPlatformCode
"s0": 3, # getPlatformCode
"s1": "",
"x0": "1", # localStorage.getItem("b1b1")
"x1": "3.3.0", # version
"x2": "Windows",
"x1": "3.7.8-2", # version
"x2": "Mac OS",
"x3": "xhs-pc-web",
"x4": "1.4.4",
"x4": "4.27.2",
"x5": a1, # cookie of a1
"x6": x_t,
"x7": x_s,
"x8": b1, # localStorage.getItem("b1")
"x9": mrc(x_t + x_s + b1),
"x10": 1, # getSigCount
"x10": 154, # getSigCount
}
encode_str = encodeUtf8(json.dumps(common, separators=(',', ':')))
x_s_common = b64Encode(encode_str)

1
store/bilibili/__init__.py
View File

@ -10,6 +10,7 @@ import config
from .bilibili_store_impl import *
from .bilibilli_store_video import *
class BiliStoreFactory:
STORES = {
"csv": BiliCsvStoreImplement,

3
store/weibo/weibo_store_impl.py
View File

@ -33,6 +33,9 @@ def calculate_number_of_files(file_store_path: str) -> int:
class WeiboCsvStoreImplement(AbstractStore):
async def store_creator(self, creator: Dict):
pass
csv_store_path: str = "data/weibo"
file_count:int=calculate_number_of_files(csv_store_path)