fork/MediaCrawler
1
0
Fork 0
mirror of https://github.com/NanmiCoder/MediaCrawler.git synced 2026-10-10 00:20:55 +08:00
Code Issues Packages Projects Releases Wiki Activity

support bilibili level two comment

Browse Source
This commit is contained in:
Nan Zhou
2024-05-26 14:10:57 +08:00
parent 764bafc626
commit 0cad36e17b
3 changed files with 111 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files
media_platform/bilibili/core.py
+35 -18
View File
@@ -49,7 +49,8 @@ class BilibiliCrawler(AbstractCrawler):
if config.ENABLE_IP_PROXY:
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.
@@ -87,27 +88,31 @@ class BilibiliCrawler(AbstractCrawler):
await self.get_specified_videos()
else:
pass
utils.logger.info("[BilibiliCrawler.start] Bilibili Crawler finished ...")
utils.logger.info(
"[BilibiliCrawler.start] Bilibili Crawler finished ...")
async def search(self):
"""
search bilibili video with keywords
:return:
"""
utils.logger.info("[BilibiliCrawler.search] Begin search bilibli keywords")
bili_limit_count =20 # bilibili limit page fixed value
utils.logger.info(
"[BilibiliCrawler.search] Begin search bilibli keywords")
bili_limit_count = 20 # bilibili limit page fixed value
if config.CRAWLER_MAX_NOTES_COUNT < bili_limit_count:
config.CRAWLER_MAX_NOTES_COUNT = bili_limit_count
start_page = self.start_page # start page number
for keyword in self.keyword.split(","):
utils.logger.info(f"[BilibiliCrawler.search] Current search keyword: {keyword}")
utils.logger.info(
f"[BilibiliCrawler.search] Current search keyword: {keyword}")
page = 1
while (page - start_page + 1) * bili_limit_count <= config.CRAWLER_MAX_NOTES_COUNT:
if page < start_page:
utils.logger.info(f"[BilibiliCrawler.search] Skip page: {page}")
utils.logger.info(
f"[BilibiliCrawler.search] Skip page: {page}")
page += 1
continue
video_id_list: List[str] = []
videos_res = await self.bili_client.search_video_by_keyword(
keyword=keyword,
@@ -119,7 +124,8 @@ class BilibiliCrawler(AbstractCrawler):
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
task_list = [
self.get_video_info_task(aid=video_item.get("aid"), bvid="", semaphore=semaphore)
self.get_video_info_task(aid=video_item.get(
"aid"), bvid="", semaphore=semaphore)
for video_item in video_list
]
video_items = await asyncio.gather(*task_list)
@@ -138,14 +144,17 @@ class BilibiliCrawler(AbstractCrawler):
:return:
"""
if not config.ENABLE_GET_COMMENTS:
utils.logger.info(f"[BilibiliCrawler.batch_get_note_comments] Crawling comment mode is not enabled")
utils.logger.info(
f"[BilibiliCrawler.batch_get_note_comments] Crawling comment mode is not enabled")
return
utils.logger.info(f"[BilibiliCrawler.batch_get_video_comments] video ids:{video_id_list}")
utils.logger.info(
f"[BilibiliCrawler.batch_get_video_comments] video ids:{video_id_list}")
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
task_list: List[Task] = []
for video_id in video_id_list:
task = asyncio.create_task(self.get_comments(video_id, semaphore), name=video_id)
task = asyncio.create_task(self.get_comments(
video_id, semaphore), name=video_id)
task_list.append(task)
await asyncio.gather(*task_list)
@@ -158,17 +167,21 @@ class BilibiliCrawler(AbstractCrawler):
"""
async with semaphore:
try:
utils.logger.info(f"[BilibiliCrawler.get_comments] begin get video_id: {video_id} comments ...")
utils.logger.info(
f"[BilibiliCrawler.get_comments] begin get video_id: {video_id} comments ...")
await self.bili_client.get_video_all_comments(
video_id=video_id,
crawl_interval=random.random(),
is_fetch_sub_comments=config.ENABLE_GET_SUB_COMMENTS,
callback=bilibili_store.batch_update_bilibili_video_comments
)
except DataFetchError as ex:
utils.logger.error(f"[BilibiliCrawler.get_comments] get video_id: {video_id} comment error: {ex}")
utils.logger.error(
f"[BilibiliCrawler.get_comments] get video_id: {video_id} comment error: {ex}")
except Exception as e:
utils.logger.error(f"[BilibiliCrawler.get_comments] may be been blocked, err:{e}")
utils.logger.error(
f"[BilibiliCrawler.get_comments] may be been blocked, err:{e}")
async def get_specified_videos(self):
"""
@@ -204,7 +217,8 @@ class BilibiliCrawler(AbstractCrawler):
result = await self.bili_client.get_video_info(aid=aid, bvid=bvid)
return result
except DataFetchError as ex:
utils.logger.error(f"[BilibiliCrawler.get_video_info_task] Get video detail error: {ex}")
utils.logger.error(
f"[BilibiliCrawler.get_video_info_task] Get video detail error: {ex}")
return None
except KeyError as ex:
utils.logger.error(
@@ -213,7 +227,8 @@ class BilibiliCrawler(AbstractCrawler):
async def create_bilibili_client(self, httpx_proxy: Optional[str]) -> BilibiliClient:
"""Create xhs client"""
utils.logger.info("[BilibiliCrawler.create_bilibili_client] Begin create bilibili API client ...")
utils.logger.info(
"[BilibiliCrawler.create_bilibili_client] Begin create bilibili API client ...")
cookie_str, cookie_dict = utils.convert_cookies(await self.browser_context.cookies())
bilibili_client_obj = BilibiliClient(
proxies=httpx_proxy,
@@ -250,7 +265,8 @@ class BilibiliCrawler(AbstractCrawler):
headless: bool = True
) -> BrowserContext:
"""Launch browser and create browser context"""
utils.logger.info("[BilibiliCrawler.launch_browser] Begin create browser context ...")
utils.logger.info(
"[BilibiliCrawler.launch_browser] Begin create browser context ...")
if config.SAVE_LOGIN_STATE:
# feat issue #14
# we will save login state to avoid login every time
@@ -266,7 +282,8 @@ class BilibiliCrawler(AbstractCrawler):
)
return browser_context
else:
browser = await chromium.launch(headless=headless, proxy=playwright_proxy) # type: ignore
# type: ignore
browser = await chromium.launch(headless=headless, proxy=playwright_proxy)
browser_context = await browser.new_context(
viewport={"width": 1920, "height": 1080},
user_agent=user_agent