jiazhizhong/MediaCrawler
1
0
Fork 0
mirror of https://github.com/NanmiCoder/MediaCrawler.git synced 2026-06-07 18:37:30 +08:00
Code Issues Packages Projects Releases Wiki Activity

添加了抖音存储视频以及图片的逻辑，并将config.py中ENABLE_GET_IMAGES参数更名为ENABLE_GET_MEIDAS，在此基础上略微修改存储逻辑

Browse Source
This commit is contained in:
未来可欺
2025-07-30 18:24:08 +08:00
parent 417c39de69
commit 173bc08a9d
12 changed files with 631 additions and 716 deletions
Download Patch File Download Diff File Expand all files Collapse all files

192
media_platform/xhs/core.py
View File

@@ -8,7 +8,6 @@
# 详细许可条款请参阅项目根目录下的LICENSE文件。
# 使用本代码即表示您同意遵守上述原则和LICENSE中的所有条款。
import asyncio
import os
import random
@@ -57,13 +56,9 @@ class XiaoHongShuCrawler(AbstractCrawler):
async def start(self) -> None:
playwright_proxy_format, httpx_proxy_format = None, None
if config.ENABLE_IP_PROXY:
ip_proxy_pool = await create_ip_pool(
config.IP_PROXY_POOL_COUNT, enable_validate_ip=True
)
ip_proxy_pool = await create_ip_pool(config.IP_PROXY_POOL_COUNT, enable_validate_ip=True)
ip_proxy_info: IpInfoModel = await ip_proxy_pool.get_proxy()
playwright_proxy_format, httpx_proxy_format = utils.format_proxy_info(
ip_proxy_info
)
playwright_proxy_format, httpx_proxy_format = utils.format_proxy_info(ip_proxy_info)
async with async_playwright() as playwright:
# 根据配置选择启动模式
@@ -101,9 +96,7 @@ class XiaoHongShuCrawler(AbstractCrawler):
cookie_str=config.COOKIES,
)
await login_obj.begin()
await self.xhs_client.update_cookies(
browser_context=self.browser_context
)
await self.xhs_client.update_cookies(browser_context=self.browser_context)
crawler_type_var.set(config.CRAWLER_TYPE)
if config.CRAWLER_TYPE == "search":
@@ -122,47 +115,33 @@ class XiaoHongShuCrawler(AbstractCrawler):
async def search(self) -> None:
"""Search for notes and retrieve their comment information."""
utils.logger.info(
"[XiaoHongShuCrawler.search] Begin search xiaohongshu keywords"
)
utils.logger.info("[XiaoHongShuCrawler.search] Begin search xiaohongshu keywords")
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
start_page = config.START_PAGE
for keyword in config.KEYWORDS.split(","):
source_keyword_var.set(keyword)
utils.logger.info(
f"[XiaoHongShuCrawler.search] Current search keyword: {keyword}"
)
utils.logger.info(f"[XiaoHongShuCrawler.search] Current search keyword: {keyword}")
page = 1
search_id = get_search_id()
while (
page - start_page + 1
) * xhs_limit_count <= config.CRAWLER_MAX_NOTES_COUNT:
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:
utils.logger.info(
f"[XiaoHongShuCrawler.search] search xhs keyword: {keyword}, page: {page}"
)
utils.logger.info(f"[XiaoHongShuCrawler.search] search xhs keyword: {keyword}, page: {page}")
note_ids: List[str] = []
xsec_tokens: List[str] = []
notes_res = await self.xhs_client.get_note_by_keyword(
keyword=keyword,
search_id=search_id,
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}"
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):
utils.logger.info("No more content!")
break
@@ -173,9 +152,7 @@ class XiaoHongShuCrawler(AbstractCrawler):
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")
) 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:
@@ -185,26 +162,18 @@ class XiaoHongShuCrawler(AbstractCrawler):
note_ids.append(note_detail.get("note_id"))
xsec_tokens.append(note_detail.get("xsec_token"))
page += 1
utils.logger.info(
f"[XiaoHongShuCrawler.search] Note details: {note_details}"
)
utils.logger.info(f"[XiaoHongShuCrawler.search] Note details: {note_details}")
await self.batch_get_note_comments(note_ids, xsec_tokens)
except DataFetchError:
utils.logger.error(
"[XiaoHongShuCrawler.search] Get note detail error"
)
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."""
utils.logger.info(
"[XiaoHongShuCrawler.get_creators_and_notes] Begin get xiaohongshu creators"
)
utils.logger.info("[XiaoHongShuCrawler.get_creators_and_notes] Begin get xiaohongshu creators")
for user_id in config.XHS_CREATOR_ID_LIST:
# get creator detail info from web html content
createor_info: Dict = await self.xhs_client.get_creator_info(
user_id=user_id
)
createor_info: Dict = await self.xhs_client.get_creator_info(user_id=user_id)
if createor_info:
await xhs_store.save_creator(user_id, creator=createor_info)
@@ -238,14 +207,14 @@ class XiaoHongShuCrawler(AbstractCrawler):
xsec_source=post_item.get("xsec_source"),
xsec_token=post_item.get("xsec_token"),
semaphore=semaphore,
)
for post_item in note_list
) for post_item in note_list
]
note_details = await asyncio.gather(*task_list)
for note_detail in note_details:
if note_detail:
await xhs_store.update_xhs_note(note_detail)
await self.get_notice_media(note_detail)
async def get_specified_notes(self):
"""
@@ -257,9 +226,7 @@ class XiaoHongShuCrawler(AbstractCrawler):
get_note_detail_task_list = []
for full_note_url in config.XHS_SPECIFIED_NOTE_URL_LIST:
note_url_info: NoteUrlInfo = parse_note_info_from_note_url(full_note_url)
utils.logger.info(
f"[XiaoHongShuCrawler.get_specified_notes] Parse note url info: {note_url_info}"
)
utils.logger.info(f"[XiaoHongShuCrawler.get_specified_notes] Parse note url info: {note_url_info}")
crawler_task = self.get_note_detail_async_task(
note_id=note_url_info.note_id,
xsec_source=note_url_info.xsec_source,
@@ -276,14 +243,15 @@ class XiaoHongShuCrawler(AbstractCrawler):
need_get_comment_note_ids.append(note_detail.get("note_id", ""))
xsec_tokens.append(note_detail.get("xsec_token", ""))
await xhs_store.update_xhs_note(note_detail)
await self.get_notice_media(note_detail)
await self.batch_get_note_comments(need_get_comment_note_ids, xsec_tokens)
async def get_note_detail_async_task(
self,
note_id: str,
xsec_source: str,
xsec_token: str,
semaphore: asyncio.Semaphore,
self,
note_id: str,
xsec_source: str,
xsec_token: str,
semaphore: asyncio.Semaphore,
) -> Optional[Dict]:
"""Get note detail
@@ -299,72 +267,49 @@ class XiaoHongShuCrawler(AbstractCrawler):
note_detail = None
async with semaphore:
try:
utils.logger.info(
f"[get_note_detail_async_task] Begin get note detail, note_id: {note_id}"
)
utils.logger.info(f"[get_note_detail_async_task] Begin get note detail, note_id: {note_id}")
try:
note_detail = await self.xhs_client.get_note_by_id(
note_id, xsec_source, xsec_token
)
note_detail = await self.xhs_client.get_note_by_id(note_id, xsec_source, xsec_token)
except RetryError as e:
pass
if not note_detail:
note_detail = await self.xhs_client.get_note_by_id_from_html(note_id, xsec_source, xsec_token,
enable_cookie=False)
note_detail = await self.xhs_client.get_note_by_id_from_html(note_id, xsec_source, xsec_token, enable_cookie=False)
if not note_detail:
raise Exception(f"[get_note_detail_async_task] Failed to get note detail, Id: {note_id}")
note_detail.update(
{"xsec_token": xsec_token, "xsec_source": xsec_source}
)
note_detail.update({"xsec_token": xsec_token, "xsec_source": xsec_source})
return note_detail
except DataFetchError as ex:
utils.logger.error(
f"[XiaoHongShuCrawler.get_note_detail_async_task] Get note detail error: {ex}"
)
utils.logger.error(f"[XiaoHongShuCrawler.get_note_detail_async_task] Get note detail error: {ex}")
return None
except KeyError as ex:
utils.logger.error(
f"[XiaoHongShuCrawler.get_note_detail_async_task] have not fund note detail note_id:{note_id}, err: {ex}"
)
utils.logger.error(f"[XiaoHongShuCrawler.get_note_detail_async_task] have not fund note detail note_id:{note_id}, err: {ex}")
return None
async def batch_get_note_comments(
self, note_list: List[str], xsec_tokens: List[str]
):
async def batch_get_note_comments(self, note_list: List[str], xsec_tokens: List[str]):
"""Batch get note comments"""
if not config.ENABLE_GET_COMMENTS:
utils.logger.info(
f"[XiaoHongShuCrawler.batch_get_note_comments] Crawling comment mode is not enabled"
)
utils.logger.info(f"[XiaoHongShuCrawler.batch_get_note_comments] Crawling comment mode is not enabled")
return
utils.logger.info(
f"[XiaoHongShuCrawler.batch_get_note_comments] Begin batch get note comments, note list: {note_list}"
)
utils.logger.info(f"[XiaoHongShuCrawler.batch_get_note_comments] Begin batch get note comments, note list: {note_list}")
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
task_list: List[Task] = []
for index, note_id in enumerate(note_list):
task = asyncio.create_task(
self.get_comments(
note_id=note_id, xsec_token=xsec_tokens[index], semaphore=semaphore
),
self.get_comments(note_id=note_id, xsec_token=xsec_tokens[index], semaphore=semaphore),
name=note_id,
)
task_list.append(task)
await asyncio.gather(*task_list)
async def get_comments(
self, note_id: str, xsec_token: str, semaphore: asyncio.Semaphore
):
async def get_comments(self, note_id: str, xsec_token: str, semaphore: asyncio.Semaphore):
"""Get note comments with keyword filtering and quantity limitation"""
async with semaphore:
utils.logger.info(
f"[XiaoHongShuCrawler.get_comments] Begin get note id comments {note_id}"
)
utils.logger.info(f"[XiaoHongShuCrawler.get_comments] Begin get note id comments {note_id}")
# When proxy is not enabled, increase the crawling interval
if config.ENABLE_IP_PROXY:
crawl_interval = random.random()
@@ -380,12 +325,8 @@ class XiaoHongShuCrawler(AbstractCrawler):
async def create_xhs_client(self, httpx_proxy: Optional[str]) -> XiaoHongShuClient:
"""Create xhs client"""
utils.logger.info(
"[XiaoHongShuCrawler.create_xhs_client] Begin create xiaohongshu API client ..."
)
cookie_str, cookie_dict = utils.convert_cookies(
await self.browser_context.cookies()
)
utils.logger.info("[XiaoHongShuCrawler.create_xhs_client] Begin create xiaohongshu API client ...")
cookie_str, cookie_dict = utils.convert_cookies(await self.browser_context.cookies())
xhs_client_obj = XiaoHongShuClient(
proxies=httpx_proxy,
headers={
@@ -412,44 +353,41 @@ class XiaoHongShuCrawler(AbstractCrawler):
return xhs_client_obj
async def launch_browser(
self,
chromium: BrowserType,
playwright_proxy: Optional[Dict],
user_agent: Optional[str],
headless: bool = True,
self,
chromium: BrowserType,
playwright_proxy: Optional[Dict],
user_agent: Optional[str],
headless: bool = True,
) -> BrowserContext:
"""Launch browser and create browser context"""
utils.logger.info(
"[XiaoHongShuCrawler.launch_browser] Begin create browser context ..."
)
utils.logger.info("[XiaoHongShuCrawler.launch_browser] Begin create browser context ...")
if config.SAVE_LOGIN_STATE:
# feat issue #14
# we will save login state to avoid login every time
user_data_dir = os.path.join(
os.getcwd(), "browser_data", config.USER_DATA_DIR % config.PLATFORM
) # type: ignore
user_data_dir = os.path.join(os.getcwd(), "browser_data", config.USER_DATA_DIR % config.PLATFORM) # type: ignore
browser_context = await chromium.launch_persistent_context(
user_data_dir=user_data_dir,
accept_downloads=True,
headless=headless,
proxy=playwright_proxy, # type: ignore
viewport={"width": 1920, "height": 1080},
viewport={
"width": 1920,
"height": 1080
},
user_agent=user_agent,
)
return browser_context
else:
browser = await chromium.launch(headless=headless, proxy=playwright_proxy) # type: ignore
browser_context = await browser.new_context(
viewport={"width": 1920, "height": 1080}, user_agent=user_agent
)
browser_context = await browser.new_context(viewport={"width": 1920, "height": 1080}, user_agent=user_agent)
return browser_context
async def launch_browser_with_cdp(
self,
playwright: Playwright,
playwright_proxy: Optional[Dict],
user_agent: Optional[str],
headless: bool = True,
self,
playwright: Playwright,
playwright_proxy: Optional[Dict],
user_agent: Optional[str],
headless: bool = True,
) -> BrowserContext:
"""
使用CDP模式启动浏览器
@@ -470,14 +408,10 @@ class XiaoHongShuCrawler(AbstractCrawler):
return browser_context
except Exception as e:
utils.logger.error(
f"[XiaoHongShuCrawler] CDP模式启动失败，回退到标准模式: {e}"
)
utils.logger.error(f"[XiaoHongShuCrawler] CDP模式启动失败，回退到标准模式: {e}")
# 回退到标准模式
chromium = playwright.chromium
return await self.launch_browser(
chromium, playwright_proxy, user_agent, headless
)
return await self.launch_browser(chromium, playwright_proxy, user_agent, headless)
async def close(self):
"""Close browser context"""
@@ -490,10 +424,8 @@ class XiaoHongShuCrawler(AbstractCrawler):
utils.logger.info("[XiaoHongShuCrawler.close] Browser context closed ...")
async def get_notice_media(self, note_detail: Dict):
if not config.ENABLE_GET_IMAGES:
utils.logger.info(
f"[XiaoHongShuCrawler.get_notice_media] Crawling image mode is not enabled"
)
if not config.ENABLE_GET_MEIDAS:
utils.logger.info(f"[XiaoHongShuCrawler.get_notice_media] Crawling image mode is not enabled")
return
await self.get_note_images(note_detail)
await self.get_notice_video(note_detail)
@@ -504,7 +436,7 @@ class XiaoHongShuCrawler(AbstractCrawler):
:param note_item:
:return:
"""
if not config.ENABLE_GET_IMAGES:
if not config.ENABLE_GET_MEIDAS:
return
note_id = note_item.get("note_id")
image_list: List[Dict] = note_item.get("image_list", [])
@@ -529,11 +461,11 @@ class XiaoHongShuCrawler(AbstractCrawler):
async def get_notice_video(self, note_item: Dict):
"""
get note images. please use get_notice_media
get note videos. please use get_notice_media
:param note_item:
:return:
"""
if not config.ENABLE_GET_IMAGES:
if not config.ENABLE_GET_MEIDAS:
return
note_id = note_item.get("note_id")
@@ -548,4 +480,4 @@ class XiaoHongShuCrawler(AbstractCrawler):
continue
extension_file_name = f"{videoNum}.mp4"
videoNum += 1
await xhs_store.update_xhs_note_image(note_id, content, extension_file_name)
await xhs_store.update_xhs_note_video(note_id, content, extension_file_name)