jiazhizhong/MediaCrawler
1
0
Fork 0
mirror of https://github.com/NanmiCoder/MediaCrawler.git synced 2026-06-08 02:47:26 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: xhs帖子详情获取优化

Browse Source
This commit is contained in:
Relakkes
2024-11-26 13:37:53 +08:00
parent de32d06815
commit 43dffeb2d1
4 changed files with 338 additions and 226 deletions
Download Patch File Download Diff File Expand all files Collapse all files

235
media_platform/xhs/core.py
View File

@@ -1,12 +1,12 @@
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
# 1. 不得用于任何商业用途。
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
# 3. 不得进行大规模爬取或对平台造成运营干扰。
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
# 声明：本代码仅供学习和研究目的使用。使用者应遵守以下原则：
# 1. 不得用于任何商业用途。
# 2. 使用时应遵守目标平台的使用条款和robots.txt规则。
# 3. 不得进行大规模爬取或对平台造成运营干扰。
# 4. 应合理控制请求频率，避免给目标平台带来不必要的负担。
# 5. 不得用于任何非法或不当的用途。
#
# 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。
#
# 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
@@ -15,8 +15,7 @@ import random
from asyncio import Task
from typing import Dict, List, Optional, Tuple
from playwright.async_api import (BrowserContext, BrowserType, Page,
async_playwright)
from playwright.async_api import BrowserContext, BrowserType, Page, async_playwright
from tenacity import RetryError
import config
@@ -48,28 +47,33 @@ 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 = self.format_proxy_info(ip_proxy_info)
playwright_proxy_format, httpx_proxy_format = self.format_proxy_info(
ip_proxy_info
)
async with async_playwright() as playwright:
# Launch a browser context.
chromium = playwright.chromium
self.browser_context = await self.launch_browser(
chromium,
None,
self.user_agent,
headless=config.HEADLESS
chromium, None, self.user_agent, headless=config.HEADLESS
)
# stealth.min.js is a js script to prevent the website from detecting the crawler.
await self.browser_context.add_init_script(path="libs/stealth.min.js")
# add a cookie attribute webId to avoid the appearance of a sliding captcha on the webpage
await self.browser_context.add_cookies([{
'name': "webId",
'value': "xxx123", # any value
'domain': ".xiaohongshu.com",
'path': "/"
}])
await self.browser_context.add_cookies(
[
{
"name": "webId",
"value": "xxx123", # any value
"domain": ".xiaohongshu.com",
"path": "/",
}
]
)
self.context_page = await self.browser_context.new_page()
await self.context_page.goto(self.index_url)
@@ -81,10 +85,12 @@ class XiaoHongShuCrawler(AbstractCrawler):
login_phone="", # input your phone number
browser_context=self.browser_context,
context_page=self.context_page,
cookie_str=config.COOKIES
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":
@@ -103,33 +109,47 @@ 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_id_list: 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,
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(
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
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
@@ -138,10 +158,10 @@ class XiaoHongShuCrawler(AbstractCrawler):
note_id=post_item.get("id"),
xsec_source=post_item.get("xsec_source"),
xsec_token=post_item.get("xsec_token"),
semaphore=semaphore
semaphore=semaphore,
)
for post_item in notes_res.get("items", {})
if post_item.get('model_type') not in ('rec_query', 'hot_query')
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:
@@ -150,18 +170,26 @@ class XiaoHongShuCrawler(AbstractCrawler):
await self.get_notice_media(note_detail)
note_id_list.append(note_detail.get("note_id"))
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_id_list)
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)
@@ -169,7 +197,7 @@ class XiaoHongShuCrawler(AbstractCrawler):
all_notes_list = await self.xhs_client.get_all_notes_by_creator(
user_id=user_id,
crawl_interval=random.random(),
callback=self.fetch_creator_notes_detail
callback=self.fetch_creator_notes_detail,
)
note_ids = [note_item.get("note_id") for note_item in all_notes_list]
@@ -185,7 +213,7 @@ class XiaoHongShuCrawler(AbstractCrawler):
note_id=post_item.get("note_id"),
xsec_source=post_item.get("xsec_source"),
xsec_token=post_item.get("xsec_token"),
semaphore=semaphore
semaphore=semaphore,
)
for post_item in note_list
]
@@ -205,12 +233,14 @@ 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,
xsec_token=note_url_info.xsec_token,
semaphore=asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
semaphore=asyncio.Semaphore(config.MAX_CONCURRENCY_NUM),
)
get_note_detail_task_list.append(crawler_task)
@@ -222,56 +252,103 @@ class XiaoHongShuCrawler(AbstractCrawler):
await xhs_store.update_xhs_note(note_detail)
await self.batch_get_note_comments(need_get_comment_note_ids)
async def get_note_detail_async_task(
self,
note_id: str,
xsec_source: str,
xsec_token: str,
semaphore: asyncio.Semaphore,
) -> Optional[Dict]:
"""Get note detail
async def get_note_detail_async_task(self, note_id: str, xsec_source: str, xsec_token: str, semaphore: asyncio.Semaphore) -> \
Optional[Dict]:
"""Get note detail"""
Args:
note_id:
xsec_source:
xsec_token:
semaphore:
Returns:
Dict: note detail
"""
note_detail_from_html, note_detail_from_api = None, None
async with semaphore:
try:
note_detail: Dict = await self.xhs_client.get_note_by_id_from_html(note_id, xsec_source, xsec_token)
# note_detail: Dict = await self.xhs_client.get_note_by_id(note_id, xsec_source, xsec_token)
if not note_detail:
# 尝试直接获取网页版笔记详情，不携带cookie
note_detail_from_html: Dict = (
await self.xhs_client.get_note_by_id_from_html(
note_id, xsec_source, xsec_token, enable_cookie=False
)
)
if not note_detail_from_html:
# 如果网页版笔记详情获取失败，则尝试使用cookie获取
note_detail_from_html = (
await self.xhs_client.get_note_by_id_from_html(
note_id, xsec_source, xsec_token, enable_cookie=True
)
)
utils.logger.error(
f"[XiaoHongShuCrawler.get_note_detail_async_task] Get note detail error, note_id: {note_id}")
f"[XiaoHongShuCrawler.get_note_detail_async_task] Get note detail error, note_id: {note_id}"
)
return None
note_detail.update({"xsec_token": xsec_token, "xsec_source": xsec_source})
return note_detail
if not note_detail_from_html:
# 如果网页版笔记详情获取失败，则尝试API获取
note_detail_from_api: Dict = await self.xhs_client.get_note_by_id(
note_id, xsec_source, xsec_token
)
note_detail = note_detail_from_html or note_detail_from_api
if note_detail:
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}")
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]):
"""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}")
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 note_id in note_list:
task = asyncio.create_task(self.get_comments(note_id, semaphore), name=note_id)
task = asyncio.create_task(
self.get_comments(note_id, semaphore), name=note_id
)
task_list.append(task)
await asyncio.gather(*task_list)
async def get_comments(self, note_id: 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}"
)
await self.xhs_client.get_note_all_comments(
note_id=note_id,
crawl_interval=random.random(),
callback=xhs_store.batch_update_xhs_note_comments,
max_count=CRAWLER_MAX_COMMENTS_COUNT_SINGLENOTES
max_count=CRAWLER_MAX_COMMENTS_COUNT_SINGLENOTES,
)
@staticmethod
def format_proxy_info(ip_proxy_info: IpInfoModel) -> Tuple[Optional[Dict], Optional[Dict]]:
def format_proxy_info(
ip_proxy_info: IpInfoModel,
) -> Tuple[Optional[Dict], Optional[Dict]]:
"""format proxy info for playwright and httpx"""
playwright_proxy = {
"server": f"{ip_proxy_info.protocol}{ip_proxy_info.ip}:{ip_proxy_info.port}",
@@ -285,8 +362,12 @@ 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={
@@ -294,7 +375,7 @@ class XiaoHongShuCrawler(AbstractCrawler):
"Cookie": cookie_str,
"Origin": "https://www.xiaohongshu.com",
"Referer": "https://www.xiaohongshu.com",
"Content-Type": "application/json;charset=UTF-8"
"Content-Type": "application/json;charset=UTF-8",
},
playwright_page=self.context_page,
cookie_dict=cookie_dict,
@@ -302,33 +383,35 @@ 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},
user_agent=user_agent
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
viewport={"width": 1920, "height": 1080}, user_agent=user_agent
)
return browser_context
@@ -339,7 +422,9 @@ class XiaoHongShuCrawler(AbstractCrawler):
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")
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)
@@ -356,8 +441,8 @@ class XiaoHongShuCrawler(AbstractCrawler):
image_list: List[Dict] = note_item.get("image_list", [])
for img in image_list:
if img.get('url_default') != '':
img.update({'url': img.get('url_default')})
if img.get("url_default") != "":
img.update({"url": img.get("url_default")})
if not image_list:
return