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

refactor: config update

Browse Source
This commit is contained in:
程序员阿江(Relakkes)
2025-07-18 23:26:52 +08:00
parent 122978b35c
commit 13b00f7a36
17 changed files with 964 additions and 485 deletions
Download Patch File Download Diff File Expand all files Collapse all files

174
media_platform/douyin/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
@@ -15,10 +15,15 @@ import random
from asyncio import Task
from typing import Any, Dict, List, Optional, Tuple
from playwright.async_api import (BrowserContext, BrowserType, Page, Playwright,
async_playwright)
from playwright.async_api import (
BrowserContext,
BrowserType,
Page,
Playwright,
async_playwright,
)
from . import config
import config
from base.base_crawler import AbstractCrawler
from proxy.proxy_ip_pool import IpInfoModel, create_ip_pool
from store import douyin as douyin_store
@@ -45,17 +50,23 @@ class DouYinCrawler(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:
# 根据配置选择启动模式
if config.ENABLE_CDP_MODE:
utils.logger.info("[DouYinCrawler] 使用CDP模式启动浏览器")
self.browser_context = await self.launch_browser_with_cdp(
playwright, playwright_proxy_format, None,
headless=config.CDP_HEADLESS
playwright,
playwright_proxy_format,
None,
headless=config.CDP_HEADLESS,
)
else:
utils.logger.info("[DouYinCrawler] 使用标准模式启动浏览器")
@@ -65,7 +76,7 @@ class DouYinCrawler(AbstractCrawler):
chromium,
playwright_proxy_format,
user_agent=None,
headless=config.HEADLESS
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")
@@ -79,10 +90,12 @@ class DouYinCrawler(AbstractCrawler):
login_phone="", # you 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.dy_client.update_cookies(browser_context=self.browser_context)
await self.dy_client.update_cookies(
browser_context=self.browser_context
)
crawler_type_var.set(config.CRAWLER_TYPE)
if config.CRAWLER_TYPE == "search":
# Search for notes and retrieve their comment information.
@@ -108,47 +121,62 @@ class DouYinCrawler(AbstractCrawler):
aweme_list: List[str] = []
page = 0
dy_search_id = ""
while (page - start_page + 1) * dy_limit_count <= config.CRAWLER_MAX_NOTES_COUNT:
while (
page - start_page + 1
) * dy_limit_count <= config.CRAWLER_MAX_NOTES_COUNT:
if page < start_page:
utils.logger.info(f"[DouYinCrawler.search] Skip {page}")
page += 1
continue
try:
utils.logger.info(f"[DouYinCrawler.search] search douyin keyword: {keyword}, page: {page}")
posts_res = await self.dy_client.search_info_by_keyword(keyword=keyword,
offset=page * dy_limit_count - dy_limit_count,
publish_time=PublishTimeType(config.PUBLISH_TIME_TYPE),
search_id=dy_search_id
)
utils.logger.info(
f"[DouYinCrawler.search] search douyin keyword: {keyword}, page: {page}"
)
posts_res = await self.dy_client.search_info_by_keyword(
keyword=keyword,
offset=page * dy_limit_count - dy_limit_count,
publish_time=PublishTimeType(config.PUBLISH_TIME_TYPE),
search_id=dy_search_id,
)
if posts_res.get("data") is None or posts_res.get("data") == []:
utils.logger.info(f"[DouYinCrawler.search] search douyin keyword: {keyword}, page: {page} is empty,{posts_res.get('data')}`")
utils.logger.info(
f"[DouYinCrawler.search] search douyin keyword: {keyword}, page: {page} is empty,{posts_res.get('data')}`"
)
break
except DataFetchError:
utils.logger.error(f"[DouYinCrawler.search] search douyin keyword: {keyword} failed")
utils.logger.error(
f"[DouYinCrawler.search] search douyin keyword: {keyword} failed"
)
break
page += 1
if "data" not in posts_res:
utils.logger.error(
f"[DouYinCrawler.search] search douyin keyword: {keyword} failed，账号也许被风控了。")
f"[DouYinCrawler.search] search douyin keyword: {keyword} failed，账号也许被风控了。"
)
break
dy_search_id = posts_res.get("extra", {}).get("logid", "")
for post_item in posts_res.get("data"):
try:
aweme_info: Dict = post_item.get("aweme_info") or \
post_item.get("aweme_mix_info", {}).get("mix_items")[0]
aweme_info: Dict = (
post_item.get("aweme_info")
or post_item.get("aweme_mix_info", {}).get("mix_items")[0]
)
except TypeError:
continue
aweme_list.append(aweme_info.get("aweme_id", ""))
await douyin_store.update_douyin_aweme(aweme_item=aweme_info)
utils.logger.info(f"[DouYinCrawler.search] keyword:{keyword}, aweme_list:{aweme_list}")
utils.logger.info(
f"[DouYinCrawler.search] keyword:{keyword}, aweme_list:{aweme_list}"
)
await self.batch_get_note_comments(aweme_list)
async def get_specified_awemes(self):
"""Get the information and comments of the specified post"""
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
task_list = [
self.get_aweme_detail(aweme_id=aweme_id, semaphore=semaphore) for aweme_id in config.DY_SPECIFIED_ID_LIST
self.get_aweme_detail(aweme_id=aweme_id, semaphore=semaphore)
for aweme_id in config.DY_SPECIFIED_ID_LIST
]
aweme_details = await asyncio.gather(*task_list)
for aweme_detail in aweme_details:
@@ -156,17 +184,22 @@ class DouYinCrawler(AbstractCrawler):
await douyin_store.update_douyin_aweme(aweme_detail)
await self.batch_get_note_comments(config.DY_SPECIFIED_ID_LIST)
async def get_aweme_detail(self, aweme_id: str, semaphore: asyncio.Semaphore) -> Any:
async def get_aweme_detail(
self, aweme_id: str, semaphore: asyncio.Semaphore
) -> Any:
"""Get note detail"""
async with semaphore:
try:
return await self.dy_client.get_video_by_id(aweme_id)
except DataFetchError as ex:
utils.logger.error(f"[DouYinCrawler.get_aweme_detail] Get aweme detail error: {ex}")
utils.logger.error(
f"[DouYinCrawler.get_aweme_detail] Get aweme detail error: {ex}"
)
return None
except KeyError as ex:
utils.logger.error(
f"[DouYinCrawler.get_aweme_detail] have not fund note detail aweme_id:{aweme_id}, err: {ex}")
f"[DouYinCrawler.get_aweme_detail] have not fund note detail aweme_id:{aweme_id}, err: {ex}"
)
return None
async def batch_get_note_comments(self, aweme_list: List[str]) -> None:
@@ -174,14 +207,17 @@ class DouYinCrawler(AbstractCrawler):
Batch get note comments
"""
if not config.ENABLE_GET_COMMENTS:
utils.logger.info(f"[DouYinCrawler.batch_get_note_comments] Crawling comment mode is not enabled")
utils.logger.info(
f"[DouYinCrawler.batch_get_note_comments] Crawling comment mode is not enabled"
)
return
task_list: List[Task] = []
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
for aweme_id in aweme_list:
task = asyncio.create_task(
self.get_comments(aweme_id, semaphore), name=aweme_id)
self.get_comments(aweme_id, semaphore), name=aweme_id
)
task_list.append(task)
if len(task_list) > 0:
await asyncio.wait(task_list)
@@ -195,18 +231,23 @@ class DouYinCrawler(AbstractCrawler):
crawl_interval=random.random(),
is_fetch_sub_comments=config.ENABLE_GET_SUB_COMMENTS,
callback=douyin_store.batch_update_dy_aweme_comments,
max_count=config.CRAWLER_MAX_COMMENTS_COUNT_SINGLENOTES
max_count=config.CRAWLER_MAX_COMMENTS_COUNT_SINGLENOTES,
)
utils.logger.info(
f"[DouYinCrawler.get_comments] aweme_id: {aweme_id} comments have all been obtained and filtered ...")
f"[DouYinCrawler.get_comments] aweme_id: {aweme_id} comments have all been obtained and filtered ..."
)
except DataFetchError as e:
utils.logger.error(f"[DouYinCrawler.get_comments] aweme_id: {aweme_id} get comments failed, error: {e}")
utils.logger.error(
f"[DouYinCrawler.get_comments] aweme_id: {aweme_id} get comments failed, error: {e}"
)
async def get_creators_and_videos(self) -> None:
"""
Get the information and videos of the specified creator
"""
utils.logger.info("[DouYinCrawler.get_creators_and_videos] Begin get douyin creators")
utils.logger.info(
"[DouYinCrawler.get_creators_and_videos] Begin get douyin creators"
)
for user_id in config.DY_CREATOR_ID_LIST:
creator_info: Dict = await self.dy_client.get_user_info(user_id)
if creator_info:
@@ -214,8 +255,7 @@ class DouYinCrawler(AbstractCrawler):
# Get all video information of the creator
all_video_list = await self.dy_client.get_all_user_aweme_posts(
sec_user_id=user_id,
callback=self.fetch_creator_video_detail
sec_user_id=user_id, callback=self.fetch_creator_video_detail
)
video_ids = [video_item.get("aweme_id") for video_item in all_video_list]
@@ -227,7 +267,8 @@ class DouYinCrawler(AbstractCrawler):
"""
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
task_list = [
self.get_aweme_detail(post_item.get("aweme_id"), semaphore) for post_item in video_list
self.get_aweme_detail(post_item.get("aweme_id"), semaphore)
for post_item in video_list
]
note_details = await asyncio.gather(*task_list)
@@ -236,7 +277,9 @@ class DouYinCrawler(AbstractCrawler):
await douyin_store.update_douyin_aweme(aweme_item)
@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}",
@@ -254,12 +297,14 @@ class DouYinCrawler(AbstractCrawler):
douyin_client = DOUYINClient(
proxies=httpx_proxy,
headers={
"User-Agent": await self.context_page.evaluate("() => navigator.userAgent"),
"User-Agent": await self.context_page.evaluate(
"() => navigator.userAgent"
),
"Cookie": cookie_str,
"Host": "www.douyin.com",
"Origin": "https://www.douyin.com/",
"Referer": "https://www.douyin.com/",
"Content-Type": "application/json;charset=UTF-8"
"Content-Type": "application/json;charset=UTF-8",
},
playwright_page=self.context_page,
cookie_dict=cookie_dict,
@@ -267,35 +312,40 @@ class DouYinCrawler(AbstractCrawler):
return douyin_client
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"""
if config.SAVE_LOGIN_STATE:
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,
) # type: ignore
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
async def launch_browser_with_cdp(self, playwright: Playwright, playwright_proxy: Optional[Dict],
user_agent: Optional[str], headless: bool = True) -> BrowserContext:
async def launch_browser_with_cdp(
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
"""
@@ -305,7 +355,7 @@ class DouYinCrawler(AbstractCrawler):
playwright=playwright,
playwright_proxy=playwright_proxy,
user_agent=user_agent,
headless=headless
headless=headless,
)
# 添加反检测脚本
@@ -321,7 +371,9 @@ class DouYinCrawler(AbstractCrawler):
utils.logger.error(f"[DouYinCrawler] 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) -> None:
"""Close browser context"""