fork/MediaCrawler
1
0
Fork 0
mirror of https://github.com/NanmiCoder/MediaCrawler.git synced 2026-09-22 04:18:11 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
eec25bb0a0276464a539415339bfa69643c6348e
MediaCrawler/media_platform/weibo/core.py
T
程序员阿江(Relakkes) 0ca7b29cf0 feat(media): 重构媒体下载，支持 xhs/dy/ks/bili/wb 五平台 
旧实现只覆盖 4 个平台，且把整个文件读进内存、无重试与完整性校验，
代码按平台复制粘贴了 4 份。本次用统一下载器替换：

- 新增 media_downloader/：流式写入、Range 续传、指数退避重试、大小校验、
  路径穿越防护；B 站 DASH 音视频分轨下载后交由 ffmpeg 无损合流
- 新增 media_platform/<平台>/media.py：从平台原始响应提取媒体地址，
  与下载器解耦；快手首次接入下载能力
- 开关：config.ENABLE_GET_MEDIA 与 --get_media，并打通 API/WebUI；
  同时修正旧配置项 ENABLE_GET_MEIDAS 的拼写
- 落盘按帖子聚合：{SAVE_DATA_PATH 或 data}/{platform}/media/{内容ID}/
- B 站装好 ffmpeg 时走 DASH 最高画质，否则降级 mp4 直链（产物 video-durl.mp4，
  避免低清文件阻塞后续的高清路径）
- 删除 4 个 *_store_media.py、AbstractStoreImage/Video 及各 client 的媒体 GET 方法

媒体下载失败只记录日志，不中断爬取主流程。
2026-09-17 22:54:22 +08:00

505 lines
22 KiB
Python
Raw Blame History

# -*- coding: utf-8 -*-
# Copyright (c) 2025 relakkes@gmail.com
#
# This file is part of MediaCrawler project.
# Repository: https://github.com/NanmiCoder/MediaCrawler/blob/main/media_platform/weibo/core.py
# GitHub: https://github.com/NanmiCoder
# Licensed under NON-COMMERCIAL LEARNING LICENSE 1.1
#
# 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。
# -*- coding: utf-8 -*-
# @Author : relakkes@gmail.com
# @Time : 2023/12/23 15:41
# @Desc : Weibo crawler main workflow code
import asyncio
import os
# import random # Removed as we now use fixed config.CRAWLER_MAX_SLEEP_SEC intervals
from asyncio import Task
from typing import Dict, List, Optional, Tuple
from playwright.async_api import (
BrowserContext,
BrowserType,
Page,
Playwright,
async_playwright,
)
import config
from base.base_crawler import AbstractCrawler
from media_downloader import MediaDownloader
from proxy.proxy_ip_pool import IpInfoModel, create_ip_pool
from store import weibo as weibo_store
from tools import utils
from tools.cdp_browser import CDPBrowserManager
from var import crawler_type_var, source_keyword_var
from . import media as weibo_media
from .client import WeiboClient
from .exception import DataFetchError
from .field import SearchType
from .help import filter_search_result_card
from .login import WeiboLogin
class WeiboCrawler(AbstractCrawler):
context_page: Page
wb_client: WeiboClient
browser_context: BrowserContext
cdp_manager: Optional[CDPBrowserManager]
def __init__(self):
self.index_url = "https://www.weibo.com"
self.mobile_index_url = "https://m.weibo.cn"
self.cookie_urls = [self.mobile_index_url]
self.user_agent = utils.get_user_agent()
self.mobile_user_agent = utils.get_mobile_user_agent()
self.cdp_manager = None
self.ip_proxy_pool = None # Proxy IP pool for automatic proxy refresh
self._media_downloader: Optional[MediaDownloader] = None
async def start(self):
playwright_proxy_format, httpx_proxy_format = None, None
if config.ENABLE_IP_PROXY:
self.ip_proxy_pool = await create_ip_pool(config.IP_PROXY_POOL_COUNT, enable_validate_ip=True)
ip_proxy_info: IpInfoModel = await self.ip_proxy_pool.get_proxy()
playwright_proxy_format, httpx_proxy_format = utils.format_proxy_info(ip_proxy_info)
async with async_playwright() as playwright:
# Select launch mode based on configuration
if config.ENABLE_CDP_MODE:
utils.logger.info("[WeiboCrawler] Launching browser with CDP mode")
self.browser_context = await self.launch_browser_with_cdp(
playwright,
playwright_proxy_format,
self.mobile_user_agent,
headless=config.CDP_HEADLESS,
)
else:
utils.logger.info("[WeiboCrawler] Launching browser with standard mode")
# Launch a browser context.
chromium = playwright.chromium
self.browser_context = await self.launch_browser(chromium, None, self.mobile_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")
self.context_page = await self.browser_context.new_page()
await self.context_page.goto(self.index_url)
await asyncio.sleep(2)
# Create a client to interact with the xiaohongshu website.
self.wb_client = await self.create_weibo_client(httpx_proxy_format)
if not await self.wb_client.pong():
login_obj = WeiboLogin(
login_type=config.LOGIN_TYPE,
login_phone="", # your phone number
browser_context=self.browser_context,
context_page=self.context_page,
cookie_str=config.COOKIES,
)
await login_obj.begin()
# After successful login, redirect to mobile website and update mobile cookies
utils.logger.info("[WeiboCrawler.start] redirect weibo mobile homepage and update cookies on mobile platform")
await self.context_page.goto(self.mobile_index_url)
await asyncio.sleep(3)
# Only get mobile cookies to avoid confusion between PC and mobile cookies
await self.wb_client.update_cookies(
browser_context=self.browser_context,
urls=self.cookie_urls,
)
crawler_type_var.set(config.CRAWLER_TYPE)
if config.CRAWLER_TYPE == "search":
# Search for video and retrieve their comment information.
await self.search()
elif config.CRAWLER_TYPE == "detail":
# Get the information and comments of the specified post
await self.get_specified_notes()
elif config.CRAWLER_TYPE == "creator":
# Get creator's information and their notes and comments
await self.get_creators_and_notes()
else:
pass
utils.logger.info("[WeiboCrawler.start] Weibo Crawler finished ...")
async def search(self):
"""
search weibo note with keywords
:return:
"""
utils.logger.info("[WeiboCrawler.search] Begin search weibo keywords")
weibo_limit_count = 10 # weibo limit page fixed value
if config.CRAWLER_MAX_NOTES_COUNT < weibo_limit_count:
config.CRAWLER_MAX_NOTES_COUNT = weibo_limit_count
start_page = config.START_PAGE
# Set the search type based on the configuration for weibo
if config.WEIBO_SEARCH_TYPE == "default":
search_type = SearchType.DEFAULT
elif config.WEIBO_SEARCH_TYPE == "real_time":
search_type = SearchType.REAL_TIME
elif config.WEIBO_SEARCH_TYPE == "popular":
search_type = SearchType.POPULAR
elif config.WEIBO_SEARCH_TYPE == "video":
search_type = SearchType.VIDEO
else:
utils.logger.error(f"[WeiboCrawler.search] Invalid WEIBO_SEARCH_TYPE: {config.WEIBO_SEARCH_TYPE}")
return
for keyword in config.KEYWORDS.split(","):
source_keyword_var.set(keyword)
utils.logger.info(f"[WeiboCrawler.search] Current search keyword: {keyword}")
page = 1
while (page - start_page + 1) * weibo_limit_count <= config.CRAWLER_MAX_NOTES_COUNT:
if page < start_page:
utils.logger.info(f"[WeiboCrawler.search] Skip page: {page}")
page += 1
continue
utils.logger.info(f"[WeiboCrawler.search] search weibo keyword: {keyword}, page: {page}")
search_res = await self.wb_client.get_note_by_keyword(keyword=keyword, page=page, search_type=search_type)
note_id_list: List[str] = []
note_list = filter_search_result_card(search_res.get("cards"))
# If full text fetching is enabled, batch get full text of posts
note_list = await self.batch_get_notes_full_text(note_list)
for note_item in note_list:
if note_item:
mblog: Dict = note_item.get("mblog")
if mblog:
note_id_list.append(mblog.get("id"))
await weibo_store.update_weibo_note(note_item)
await self.download_media(mblog)
page += 1
# Sleep after page navigation
await asyncio.sleep(config.CRAWLER_MAX_SLEEP_SEC)
utils.logger.info(f"[WeiboCrawler.search] Sleeping for {config.CRAWLER_MAX_SLEEP_SEC} seconds after page {page-1}")
await self.batch_get_notes_comments(note_id_list)
async def get_specified_notes(self):
"""
get specified notes info
:return:
"""
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
task_list = [self.get_note_info_task(note_id=note_id, semaphore=semaphore) for note_id in config.WEIBO_SPECIFIED_ID_LIST]
video_details = await asyncio.gather(*task_list)
for note_item in video_details:
if note_item:
await weibo_store.update_weibo_note(note_item)
mblog = note_item.get("mblog")
if mblog:
await self.download_media(mblog)
await self.batch_get_notes_comments(config.WEIBO_SPECIFIED_ID_LIST)
async def get_note_info_task(self, note_id: str, semaphore: asyncio.Semaphore) -> Optional[Dict]:
"""
Get note detail task
:param note_id:
:param semaphore:
:return:
"""
async with semaphore:
try:
result = await self.wb_client.get_note_info_by_id(note_id)
# Sleep after fetching note details
await asyncio.sleep(config.CRAWLER_MAX_SLEEP_SEC)
utils.logger.info(f"[WeiboCrawler.get_note_info_task] Sleeping for {config.CRAWLER_MAX_SLEEP_SEC} seconds after fetching note details {note_id}")
return result
except DataFetchError as ex:
utils.logger.error(f"[WeiboCrawler.get_note_info_task] Get note detail error: {ex}")
return None
except KeyError as ex:
utils.logger.error(f"[WeiboCrawler.get_note_info_task] have not fund note detail note_id:{note_id}, err: {ex}")
return None
async def batch_get_notes_comments(self, note_id_list: List[str]):
"""
batch get notes comments
:param note_id_list:
:return:
"""
if not config.ENABLE_GET_COMMENTS:
utils.logger.info(f"[WeiboCrawler.batch_get_note_comments] Crawling comment mode is not enabled")
return
utils.logger.info(f"[WeiboCrawler.batch_get_notes_comments] note ids:{note_id_list}")
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
task_list: List[Task] = []
for note_id in note_id_list:
task = asyncio.create_task(self.get_note_comments(note_id, semaphore), name=note_id)
task_list.append(task)
await asyncio.gather(*task_list)
async def get_note_comments(self, note_id: str, semaphore: asyncio.Semaphore):
"""
get comment for note id
:param note_id:
:param semaphore:
:return:
"""
async with semaphore:
try:
utils.logger.info(f"[WeiboCrawler.get_note_comments] begin get note_id: {note_id} comments ...")
# Sleep before fetching comments
await asyncio.sleep(config.CRAWLER_MAX_SLEEP_SEC)
utils.logger.info(f"[WeiboCrawler.get_note_comments] Sleeping for {config.CRAWLER_MAX_SLEEP_SEC} seconds before fetching comments for note {note_id}")
await self.wb_client.get_note_all_comments(
note_id=note_id,
crawl_interval=config.CRAWLER_MAX_SLEEP_SEC, # Use fixed interval instead of random
callback=weibo_store.batch_update_weibo_note_comments,
max_count=config.CRAWLER_MAX_COMMENTS_COUNT_SINGLENOTES,
)
except DataFetchError as ex:
utils.logger.error(f"[WeiboCrawler.get_note_comments] get note_id: {note_id} comment error: {ex}")
except Exception as e:
utils.logger.error(f"[WeiboCrawler.get_note_comments] may be been blocked, err:{e}")
async def download_media(self, mblog: Dict) -> None:
"""下载微博的媒体资源（配图，或视频 + 封面）
:param mblog: 微博正文数据
"""
if not config.ENABLE_GET_MEDIA:
return
try:
items = weibo_media.build_media_items(mblog)
if items:
await self._get_media_downloader().download_all(items)
except Exception as exc:
# 媒体下载是旁路能力，解析异常/网络异常都不能中断爬取主流程
utils.logger.error(f"[WeiboCrawler.download_media] 媒体下载异常: {exc}")
def _get_media_downloader(self) -> MediaDownloader:
"""惰性创建媒体下载器，并同步最新的代理与 UA（代理池是就地刷新的）"""
if self._media_downloader is None:
self._media_downloader = MediaDownloader(
platform="wb",
proxy=getattr(self.wb_client, "proxy", None),
extra_headers=self._media_headers(),
)
else:
self._media_downloader.update_credentials(
proxy=getattr(self.wb_client, "proxy", None),
extra_headers=self._media_headers(),
)
return self._media_downloader
def _media_headers(self) -> Dict:
"""媒体请求头：平台 Referer（防盗链）+ UA。
client.headers 里含 Cookie，不能整体透传到 CDN 请求上，因此只取 UA。
"""
headers = {"Referer": "https://weibo.com/"}
client_headers = getattr(self.wb_client, "headers", {}) or {}
if client_headers.get("User-Agent"):
headers["User-Agent"] = client_headers["User-Agent"]
return headers
async def get_creators_and_notes(self) -> None:
"""
Get creator's information and their notes and comments
Returns:
"""
utils.logger.info("[WeiboCrawler.get_creators_and_notes] Begin get weibo creators")
for user_id in config.WEIBO_CREATOR_ID_LIST:
createor_info_res: Dict = await self.wb_client.get_creator_info_by_id(creator_id=user_id)
if createor_info_res:
createor_info: Dict = createor_info_res.get("userInfo", {})
utils.logger.info(f"[WeiboCrawler.get_creators_and_notes] creator info: {createor_info}")
if not createor_info:
raise DataFetchError("Get creator info error")
await weibo_store.save_creator(user_id, user_info=createor_info)
# Create a wrapper callback to get full text before saving data
async def save_notes_with_full_text(note_list: List[Dict]):
# If full text fetching is enabled, batch get full text first
updated_note_list = await self.batch_get_notes_full_text(note_list)
await weibo_store.batch_update_weibo_notes(updated_note_list)
for note_item in updated_note_list:
mblog = (note_item or {}).get("mblog")
if mblog:
await self.download_media(mblog)
# Get all note information of the creator
all_notes_list = await self.wb_client.get_all_notes_by_creator_id(
creator_id=user_id,
container_id=f"107603{user_id}",
crawl_interval=0,
callback=save_notes_with_full_text,
)
note_ids = [note_item.get("mblog", {}).get("id") for note_item in all_notes_list if note_item.get("mblog", {}).get("id")]
await self.batch_get_notes_comments(note_ids)
else:
utils.logger.error(f"[WeiboCrawler.get_creators_and_notes] get creator info error, creator_id:{user_id}")
async def create_weibo_client(self, httpx_proxy: Optional[str]) -> WeiboClient:
"""Create xhs client"""
utils.logger.info("[WeiboCrawler.create_weibo_client] Begin create weibo API client ...")
cookie_str, cookie_dict = await utils.convert_browser_context_cookies(
self.browser_context,
urls=self.cookie_urls,
)
weibo_client_obj = WeiboClient(
proxy=httpx_proxy,
headers={
"User-Agent": utils.get_mobile_user_agent(),
"Cookie": cookie_str,
"Origin": "https://m.weibo.cn",
"Referer": "https://m.weibo.cn",
"Content-Type": "application/json;charset=UTF-8",
},
playwright_page=self.context_page,
cookie_dict=cookie_dict,
proxy_ip_pool=self.ip_proxy_pool, # Pass proxy pool for automatic refresh
)
return weibo_client_obj
async def launch_browser(
self,
chromium: BrowserType,
playwright_proxy: Optional[Dict],
user_agent: Optional[str],
headless: bool = True,
) -> BrowserContext:
"""Launch browser and create browser context"""
utils.logger.info("[WeiboCrawler.launch_browser] Begin create browser context ...")
if config.SAVE_LOGIN_STATE:
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,
channel="chrome", # Use system's Chrome stable version
)
return browser_context
else:
browser = await chromium.launch(headless=headless, proxy=playwright_proxy, channel="chrome") # type: ignore
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,
) -> BrowserContext:
"""
Launch browser with CDP mode
"""
try:
self.cdp_manager = CDPBrowserManager()
browser_context = await self.cdp_manager.launch_and_connect(
playwright=playwright,
playwright_proxy=playwright_proxy,
user_agent=user_agent,
headless=headless,
)
# Display browser information
browser_info = await self.cdp_manager.get_browser_info()
utils.logger.info(f"[WeiboCrawler] CDP browser info: {browser_info}")
return browser_context
except Exception as e:
utils.logger.error(f"[WeiboCrawler] CDP mode startup failed, falling back to standard mode: {e}")
# Fallback to standard mode
chromium = playwright.chromium
return await self.launch_browser(chromium, playwright_proxy, user_agent, headless)
async def get_note_full_text(self, note_item: Dict) -> Dict:
"""
Get full text content of a post
If the post content is truncated (isLongText=True), request the detail API to get complete content
:param note_item: Post data, contains mblog field
:return: Updated post data
"""
if not config.ENABLE_WEIBO_FULL_TEXT:
return note_item
mblog = note_item.get("mblog", {})
if not mblog:
return note_item
# Check if it's a long text
is_long_text = mblog.get("isLongText", False)
if not is_long_text:
return note_item
note_id = mblog.get("id")
if not note_id:
return note_item
try:
utils.logger.info(f"[WeiboCrawler.get_note_full_text] Fetching full text for note: {note_id}")
full_note = await self.wb_client.get_note_info_by_id(note_id)
if full_note and full_note.get("mblog"):
# Replace original content with complete content
note_item["mblog"] = full_note["mblog"]
utils.logger.info(f"[WeiboCrawler.get_note_full_text] Successfully fetched full text for note: {note_id}")
# Sleep after request to avoid rate limiting
await asyncio.sleep(config.CRAWLER_MAX_SLEEP_SEC)
except DataFetchError as ex:
utils.logger.error(f"[WeiboCrawler.get_note_full_text] Failed to fetch full text for note {note_id}: {ex}")
except Exception as ex:
utils.logger.error(f"[WeiboCrawler.get_note_full_text] Unexpected error for note {note_id}: {ex}")
return note_item
async def batch_get_notes_full_text(self, note_list: List[Dict]) -> List[Dict]:
"""
Batch get full text content of posts
:param note_list: List of posts
:return: Updated list of posts
"""
if not config.ENABLE_WEIBO_FULL_TEXT:
return note_list
result = []
for note_item in note_list:
updated_note = await self.get_note_full_text(note_item)
result.append(updated_note)
return result
async def close(self):
"""Close browser context"""
# Special handling if using CDP mode
if self.cdp_manager:
await self.cdp_manager.cleanup()
self.cdp_manager = None
else:
await self.browser_context.close()
utils.logger.info("[WeiboCrawler.close] Browser context closed ...")
Reference in New Issue View Git Blame Copy Permalink