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

feat(core): 新增控制爬虫 参数起始页面的页数start_page;perf(argparse): 向命令行解析器添加程序参数起始页面页数和关键字

Browse Source
This commit is contained in:
Tianci-King
2024-04-12 00:52:47 +08:00
parent bba9841c26
commit 1115b0d90c
9 changed files with 94 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files

60
media_platform/xhs/core.py
View File

@@ -32,10 +32,12 @@ class XiaoHongShuCrawler(AbstractCrawler):
self.index_url = "https://www.xiaohongshu.com"
self.user_agent = utils.get_user_agent()
def init_config(self, platform: str, login_type: str, crawler_type: str) -> None:
def init_config(self, platform: str, login_type: str, crawler_type: str, start_page: int, keyword: str) -> None:
self.platform = platform
self.login_type = login_type
self.crawler_type = crawler_type
self.start_page = start_page
self.keyword = keyword
async def start(self) -> None:
playwright_proxy_format, httpx_proxy_format = None, None
@@ -99,31 +101,41 @@ class XiaoHongShuCrawler(AbstractCrawler):
xhs_limit_count = 20 # xhs limit page fixed value
if config.CRAWLER_MAX_NOTES_COUNT < xhs_limit_count:
config.CRAWLER_MAX_NOTES_COUNT = xhs_limit_count
for keyword in config.KEYWORDS.split(","):
start_page = self.start_page
for keyword in self.keyword.split(","):
utils.logger.info(f"[XiaoHongShuCrawler.search] Current search keyword: {keyword}")
page = 1
while page * xhs_limit_count <= config.CRAWLER_MAX_NOTES_COUNT:
note_id_list: List[str] = []
notes_res = await self.xhs_client.get_note_by_keyword(
keyword=keyword,
page=page,
sort=SearchSortType(config.SORT_TYPE) if config.SORT_TYPE != '' else SearchSortType.GENERAL,
)
utils.logger.info(f"[XiaoHongShuCrawler.search] Search notes res:{notes_res}")
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
task_list = [
self.get_note_detail(post_item.get("id"), 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:
await xhs_store.update_xhs_note(note_detail)
note_id_list.append(note_detail.get("note_id"))
page += 1
utils.logger.info(f"[XiaoHongShuCrawler.search] Note details: {note_details}")
await self.batch_get_note_comments(note_id_list)
while (page - start_page + 1) * xhs_limit_count <= config.CRAWLER_MAX_NOTES_COUNT:
if page < start_page:
utils.logger.info(f"[XiaoHongShuCrawler.search] Skip page {page}")
page += 1
continue
try:
note_id_list: List[str] = []
notes_res = await self.xhs_client.get_note_by_keyword(
keyword=keyword,
page=page,
sort=SearchSortType(config.SORT_TYPE) if config.SORT_TYPE != '' else SearchSortType.GENERAL,
)
utils.logger.info(f"[XiaoHongShuCrawler.search] Search notes res:{notes_res}")
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
task_list = [
self.get_note_detail(post_item.get("id"), 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:
await xhs_store.update_xhs_note(note_detail)
note_id_list.append(note_detail.get("note_id"))
page += 1
utils.logger.info(f"[XiaoHongShuCrawler.search] Note details: {note_details}")
await self.batch_get_note_comments(note_id_list)
except DataFetchError:
utils.logger.error("[XiaoHongShuCrawler.search] Get note detail error")
break
async def get_creators_and_notes(self) -> None:
"""Get creator's notes and retrieve their comment information."""