jiazhizhong/MediaCrawler
1
0
Fork 0
mirror of https://github.com/NanmiCoder/MediaCrawler.git synced 2026-04-21 19:27:40 +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

322
media_platform/bilibili/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。
# -*- coding: utf-8 -*-
# @Author : relakkes@gmail.com
# @Time : 2023/12/2 18:44
@@ -59,13 +58,9 @@ class BilibiliCrawler(AbstractCrawler):
async def start(self):
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
@@ -81,9 +76,7 @@ class BilibiliCrawler(AbstractCrawler):
utils.logger.info("[BilibiliCrawler] 使用标准模式启动浏览器")
# Launch a browser context.
chromium = playwright.chromium
self.browser_context = await self.launch_browser(
chromium, None, self.user_agent, headless=config.HEADLESS
)
self.browser_context = await self.launch_browser(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")
self.context_page = await self.browser_context.new_page()
@@ -100,9 +93,7 @@ class BilibiliCrawler(AbstractCrawler):
cookie_str=config.COOKIES,
)
await login_obj.begin()
await self.bili_client.update_cookies(
browser_context=self.browser_context
)
await self.bili_client.update_cookies(browser_context=self.browser_context)
crawler_type_var.set(config.CRAWLER_TYPE)
if config.CRAWLER_TYPE == "search":
@@ -136,7 +127,8 @@ class BilibiliCrawler(AbstractCrawler):
@staticmethod
async def get_pubtime_datetime(
start: str = config.START_DAY, end: str = config.END_DAY
start: str = config.START_DAY,
end: str = config.END_DAY,
) -> Tuple[str, str]:
"""
获取 bilibili 作品发布日期起始时间戳 pubtime_begin_s 与发布日期结束时间戳 pubtime_end_s
@@ -158,17 +150,11 @@ class BilibiliCrawler(AbstractCrawler):
start_day: datetime = datetime.strptime(start, "%Y-%m-%d")
end_day: datetime = datetime.strptime(end, "%Y-%m-%d")
if start_day > end_day:
raise ValueError(
"Wrong time range, please check your start and end argument, to ensure that the start cannot exceed end"
)
raise ValueError("Wrong time range, please check your start and end argument, to ensure that the start cannot exceed end")
elif start_day == end_day: # 搜索同一天的内容
end_day = (
start_day + timedelta(days=1) - timedelta(seconds=1)
) # 则将 end_day 设置为 start_day + 1 day - 1 second
end_day = (start_day + timedelta(days=1) - timedelta(seconds=1)) # 则将 end_day 设置为 start_day + 1 day - 1 second
else: # 搜索 start 至 end
end_day = (
end_day + timedelta(days=1) - timedelta(seconds=1)
) # 则将 end_day 设置为 end_day + 1 day - 1 second
end_day = (end_day + timedelta(days=1) - timedelta(seconds=1)) # 则将 end_day 设置为 end_day + 1 day - 1 second
# 将其重新转换为时间戳
return str(int(start_day.timestamp())), str(int(end_day.timestamp()))
@@ -177,32 +163,22 @@ class BilibiliCrawler(AbstractCrawler):
search bilibili video with keywords in normal mode
:return:
"""
utils.logger.info(
"[BilibiliCrawler.search_by_keywords] Begin search bilibli keywords"
)
utils.logger.info("[BilibiliCrawler.search_by_keywords] 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 = config.START_PAGE # start page number
for keyword in config.KEYWORDS.split(","):
source_keyword_var.set(keyword)
utils.logger.info(
f"[BilibiliCrawler.search_by_keywords] Current search keyword: {keyword}"
)
utils.logger.info(f"[BilibiliCrawler.search_by_keywords] Current search keyword: {keyword}")
page = 1
while (
page - start_page + 1
) * bili_limit_count <= config.CRAWLER_MAX_NOTES_COUNT:
while (page - start_page + 1) * bili_limit_count <= config.CRAWLER_MAX_NOTES_COUNT:
if page < start_page:
utils.logger.info(
f"[BilibiliCrawler.search_by_keywords] Skip page: {page}"
)
utils.logger.info(f"[BilibiliCrawler.search_by_keywords] Skip page: {page}")
page += 1
continue
utils.logger.info(
f"[BilibiliCrawler.search_by_keywords] search bilibili keyword: {keyword}, page: {page}"
)
utils.logger.info(f"[BilibiliCrawler.search_by_keywords] search bilibili keyword: {keyword}, page: {page}")
video_id_list: List[str] = []
videos_res = await self.bili_client.search_video_by_keyword(
keyword=keyword,
@@ -215,24 +191,15 @@ class BilibiliCrawler(AbstractCrawler):
video_list: List[Dict] = videos_res.get("result")
if not video_list:
utils.logger.info(
f"[BilibiliCrawler.search_by_keywords] No more videos for '{keyword}', moving to next keyword."
)
utils.logger.info(f"[BilibiliCrawler.search_by_keywords] No more videos for '{keyword}', moving to next keyword.")
break
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
task_list = []
try:
task_list = [
self.get_video_info_task(
aid=video_item.get("aid"), bvid="", semaphore=semaphore
)
for video_item in video_list
]
task_list = [self.get_video_info_task(aid=video_item.get("aid"), bvid="", semaphore=semaphore) for video_item in video_list]
except Exception as e:
utils.logger.warning(
f"[BilibiliCrawler.search_by_keywords] error in the task list. The video for this page will not be included. {e}"
)
utils.logger.warning(f"[BilibiliCrawler.search_by_keywords] error in the task list. The video for this page will not be included. {e}")
video_items = await asyncio.gather(*task_list)
for video_item in video_items:
if video_item:
@@ -248,74 +215,40 @@ class BilibiliCrawler(AbstractCrawler):
Search bilibili video with keywords in a given time range.
:param daily_limit: if True, strictly limit the number of notes per day and total.
"""
utils.logger.info(
f"[BilibiliCrawler.search_by_keywords_in_time_range] Begin search with daily_limit={daily_limit}"
)
utils.logger.info(f"[BilibiliCrawler.search_by_keywords_in_time_range] Begin search with daily_limit={daily_limit}")
bili_limit_count = 20
start_page = config.START_PAGE
for keyword in config.KEYWORDS.split(","):
source_keyword_var.set(keyword)
utils.logger.info(
f"[BilibiliCrawler.search_by_keywords_in_time_range] Current search keyword: {keyword}"
)
utils.logger.info(f"[BilibiliCrawler.search_by_keywords_in_time_range] Current search keyword: {keyword}")
total_notes_crawled_for_keyword = 0
for day in pd.date_range(
start=config.START_DAY, end=config.END_DAY, freq="D"
):
if (
daily_limit
and total_notes_crawled_for_keyword
>= config.CRAWLER_MAX_NOTES_COUNT
):
utils.logger.info(
f"[BilibiliCrawler.search] Reached CRAWLER_MAX_NOTES_COUNT limit for keyword '{keyword}', skipping remaining days."
)
for day in pd.date_range(start=config.START_DAY, end=config.END_DAY, freq="D"):
if (daily_limit and total_notes_crawled_for_keyword >= config.CRAWLER_MAX_NOTES_COUNT):
utils.logger.info(f"[BilibiliCrawler.search] Reached CRAWLER_MAX_NOTES_COUNT limit for keyword '{keyword}', skipping remaining days.")
break
if (
not daily_limit
and total_notes_crawled_for_keyword
>= config.CRAWLER_MAX_NOTES_COUNT
):
utils.logger.info(
f"[BilibiliCrawler.search] Reached CRAWLER_MAX_NOTES_COUNT limit for keyword '{keyword}', skipping remaining days."
)
if (not daily_limit and total_notes_crawled_for_keyword >= config.CRAWLER_MAX_NOTES_COUNT):
utils.logger.info(f"[BilibiliCrawler.search] Reached CRAWLER_MAX_NOTES_COUNT limit for keyword '{keyword}', skipping remaining days.")
break
pubtime_begin_s, pubtime_end_s = await self.get_pubtime_datetime(
start=day.strftime("%Y-%m-%d"), end=day.strftime("%Y-%m-%d")
)
pubtime_begin_s, pubtime_end_s = await self.get_pubtime_datetime(start=day.strftime("%Y-%m-%d"), end=day.strftime("%Y-%m-%d"))
page = 1
notes_count_this_day = 0
while True:
if notes_count_this_day >= config.MAX_NOTES_PER_DAY:
utils.logger.info(
f"[BilibiliCrawler.search] Reached MAX_NOTES_PER_DAY limit for {day.ctime()}."
)
utils.logger.info(f"[BilibiliCrawler.search] Reached MAX_NOTES_PER_DAY limit for {day.ctime()}.")
break
if (
daily_limit
and total_notes_crawled_for_keyword
>= config.CRAWLER_MAX_NOTES_COUNT
):
utils.logger.info(
f"[BilibiliCrawler.search] Reached CRAWLER_MAX_NOTES_COUNT limit for keyword '{keyword}'."
)
if (daily_limit and total_notes_crawled_for_keyword >= config.CRAWLER_MAX_NOTES_COUNT):
utils.logger.info(f"[BilibiliCrawler.search] Reached CRAWLER_MAX_NOTES_COUNT limit for keyword '{keyword}'.")
break
if (
not daily_limit
and total_notes_crawled_for_keyword
>= config.CRAWLER_MAX_NOTES_COUNT
):
if (not daily_limit and total_notes_crawled_for_keyword >= config.CRAWLER_MAX_NOTES_COUNT):
break
try:
utils.logger.info(
f"[BilibiliCrawler.search] search bilibili keyword: {keyword}, date: {day.ctime()}, page: {page}"
)
utils.logger.info(f"[BilibiliCrawler.search] search bilibili keyword: {keyword}, date: {day.ctime()}, page: {page}")
video_id_list: List[str] = []
videos_res = await self.bili_client.search_video_by_keyword(
keyword=keyword,
@@ -328,33 +261,18 @@ class BilibiliCrawler(AbstractCrawler):
video_list: List[Dict] = videos_res.get("result")
if not video_list:
utils.logger.info(
f"[BilibiliCrawler.search] No more videos for '{keyword}' on {day.ctime()}, moving to next day."
)
utils.logger.info(f"[BilibiliCrawler.search] No more videos for '{keyword}' on {day.ctime()}, moving to next day.")
break
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
task_list = [
self.get_video_info_task(
aid=video_item.get("aid"), bvid="", semaphore=semaphore
)
for video_item in video_list
]
task_list = [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)
for video_item in video_items:
if video_item:
if (
daily_limit
and total_notes_crawled_for_keyword
>= config.CRAWLER_MAX_NOTES_COUNT
):
if (daily_limit and total_notes_crawled_for_keyword >= config.CRAWLER_MAX_NOTES_COUNT):
break
if (
not daily_limit
and total_notes_crawled_for_keyword
>= config.CRAWLER_MAX_NOTES_COUNT
):
if (not daily_limit and total_notes_crawled_for_keyword >= config.CRAWLER_MAX_NOTES_COUNT):
break
if notes_count_this_day >= config.MAX_NOTES_PER_DAY:
break
@@ -369,9 +287,7 @@ class BilibiliCrawler(AbstractCrawler):
await self.batch_get_video_comments(video_id_list)
except Exception as e:
utils.logger.error(
f"[BilibiliCrawler.search] Error searching on {day.ctime()}: {e}"
)
utils.logger.error(f"[BilibiliCrawler.search] Error searching on {day.ctime()}: {e}")
break
async def batch_get_video_comments(self, video_id_list: List[str]):
@@ -381,20 +297,14 @@ 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)
@@ -407,9 +317,7 @@ 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 asyncio.sleep(random.uniform(0.5, 1.5))
await self.bili_client.get_video_all_comments(
video_id=video_id,
@@ -420,13 +328,9 @@ class BilibiliCrawler(AbstractCrawler):
)
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}")
# Propagate the exception to be caught by the main loop
raise
@@ -452,10 +356,7 @@ class BilibiliCrawler(AbstractCrawler):
:return:
"""
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
task_list = [
self.get_video_info_task(aid=0, bvid=video_id, semaphore=semaphore)
for video_id in bvids_list
]
task_list = [self.get_video_info_task(aid=0, bvid=video_id, semaphore=semaphore) for video_id in bvids_list]
video_details = await asyncio.gather(*task_list)
video_aids_list = []
for video_detail in video_details:
@@ -469,9 +370,7 @@ class BilibiliCrawler(AbstractCrawler):
await self.get_bilibili_video(video_detail, semaphore)
await self.batch_get_video_comments(video_aids_list)
async def get_video_info_task(
self, aid: int, bvid: str, semaphore: asyncio.Semaphore
) -> Optional[Dict]:
async def get_video_info_task(self, aid: int, bvid: str, semaphore: asyncio.Semaphore) -> Optional[Dict]:
"""
Get video detail task
:param aid:
@@ -484,19 +383,13 @@ 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(
f"[BilibiliCrawler.get_video_info_task] have not fund note detail video_id:{bvid}, err: {ex}"
)
utils.logger.error(f"[BilibiliCrawler.get_video_info_task] have not fund note detail video_id:{bvid}, err: {ex}")
return None
async def get_video_play_url_task(
self, aid: int, cid: int, semaphore: asyncio.Semaphore
) -> Union[Dict, None]:
async def get_video_play_url_task(self, aid: int, cid: int, semaphore: asyncio.Semaphore) -> Union[Dict, None]:
"""
Get video play url
:param aid:
@@ -509,30 +402,20 @@ class BilibiliCrawler(AbstractCrawler):
result = await self.bili_client.get_video_play_url(aid=aid, cid=cid)
return result
except DataFetchError as ex:
utils.logger.error(
f"[BilibiliCrawler.get_video_play_url_task] Get video play url error: {ex}"
)
utils.logger.error(f"[BilibiliCrawler.get_video_play_url_task] Get video play url error: {ex}")
return None
except KeyError as ex:
utils.logger.error(
f"[BilibiliCrawler.get_video_play_url_task] have not fund play url from :{aid}|{cid}, err: {ex}"
)
utils.logger.error(f"[BilibiliCrawler.get_video_play_url_task] have not fund play url from :{aid}|{cid}, err: {ex}")
return None
async def create_bilibili_client(
self, httpx_proxy: Optional[str]
) -> BilibiliClient:
async def create_bilibili_client(self, httpx_proxy: Optional[str]) -> BilibiliClient:
"""
create bilibili client
:param httpx_proxy: httpx proxy
:return: bilibili 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()
)
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,
headers={
@@ -562,30 +445,27 @@ class BilibiliCrawler(AbstractCrawler):
:param headless: headless mode
:return: 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
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:
# 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
)
browser_context = await browser.new_context(viewport={"width": 1920, "height": 1080}, user_agent=user_agent)
return browser_context
async def launch_browser_with_cdp(
@@ -614,14 +494,10 @@ class BilibiliCrawler(AbstractCrawler):
return browser_context
except Exception as e:
utils.logger.error(
f"[BilibiliCrawler] CDP模式启动失败，回退到标准模式: {e}"
)
utils.logger.error(f"[BilibiliCrawler] 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"""
@@ -634,13 +510,9 @@ class BilibiliCrawler(AbstractCrawler):
await self.browser_context.close()
utils.logger.info("[BilibiliCrawler.close] Browser context closed ...")
except TargetClosedError:
utils.logger.warning(
"[BilibiliCrawler.close] Browser context was already closed."
)
utils.logger.warning("[BilibiliCrawler.close] Browser context was already closed.")
except Exception as e:
utils.logger.error(
f"[BilibiliCrawler.close] An error occurred during close: {e}"
)
utils.logger.error(f"[BilibiliCrawler.close] An error occurred during close: {e}")
async def get_bilibili_video(self, video_item: Dict, semaphore: asyncio.Semaphore):
"""
@@ -649,19 +521,15 @@ class BilibiliCrawler(AbstractCrawler):
:param semaphore:
:return:
"""
if not config.ENABLE_GET_IMAGES:
utils.logger.info(
f"[BilibiliCrawler.get_bilibili_video] Crawling image mode is not enabled"
)
if not config.ENABLE_GET_MEIDAS:
utils.logger.info(f"[BilibiliCrawler.get_bilibili_video] Crawling image mode is not enabled")
return
video_item_view: Dict = video_item.get("View")
aid = video_item_view.get("aid")
cid = video_item_view.get("cid")
result = await self.get_video_play_url_task(aid, cid, semaphore)
if result is None:
utils.logger.info(
"[BilibiliCrawler.get_bilibili_video] get video play url failed"
)
utils.logger.info("[BilibiliCrawler.get_bilibili_video] get video play url failed")
return
durl_list = result.get("durl")
max_size = -1
@@ -672,9 +540,7 @@ class BilibiliCrawler(AbstractCrawler):
max_size = size
video_url = durl.get("url")
if video_url == "":
utils.logger.info(
"[BilibiliCrawler.get_bilibili_video] get video url failed"
)
utils.logger.info("[BilibiliCrawler.get_bilibili_video] get video url failed")
return
content = await self.bili_client.get_video_media(video_url)
@@ -687,25 +553,17 @@ class BilibiliCrawler(AbstractCrawler):
"""
creator_id_list: get details for creator from creator_id_list
"""
utils.logger.info(
f"[BilibiliCrawler.get_creator_details] Crawling the detalis of creator"
)
utils.logger.info(
f"[BilibiliCrawler.get_creator_details] creator ids:{creator_id_list}"
)
utils.logger.info(f"[BilibiliCrawler.get_creator_details] Crawling the detalis of creator")
utils.logger.info(f"[BilibiliCrawler.get_creator_details] creator ids:{creator_id_list}")
semaphore = asyncio.Semaphore(config.MAX_CONCURRENCY_NUM)
task_list: List[Task] = []
try:
for creator_id in creator_id_list:
task = asyncio.create_task(
self.get_creator_details(creator_id, semaphore), name=creator_id
)
task = asyncio.create_task(self.get_creator_details(creator_id, semaphore), name=creator_id)
task_list.append(task)
except Exception as e:
utils.logger.warning(
f"[BilibiliCrawler.get_all_creator_details] error in the task list. The creator will not be included. {e}"
)
utils.logger.warning(f"[BilibiliCrawler.get_all_creator_details] error in the task list. The creator will not be included. {e}")
await asyncio.gather(*task_list)
@@ -717,9 +575,7 @@ class BilibiliCrawler(AbstractCrawler):
:return:
"""
async with semaphore:
creator_unhandled_info: Dict = await self.bili_client.get_creator_info(
creator_id
)
creator_unhandled_info: Dict = await self.bili_client.get_creator_info(creator_id)
creator_info: Dict = {
"id": creator_id,
"name": creator_unhandled_info.get("name"),
@@ -740,9 +596,7 @@ class BilibiliCrawler(AbstractCrawler):
creator_id = creator_info["id"]
async with semaphore:
try:
utils.logger.info(
f"[BilibiliCrawler.get_fans] begin get creator_id: {creator_id} fans ..."
)
utils.logger.info(f"[BilibiliCrawler.get_fans] begin get creator_id: {creator_id} fans ...")
await self.bili_client.get_creator_all_fans(
creator_info=creator_info,
crawl_interval=random.random(),
@@ -751,13 +605,9 @@ class BilibiliCrawler(AbstractCrawler):
)
except DataFetchError as ex:
utils.logger.error(
f"[BilibiliCrawler.get_fans] get creator_id: {creator_id} fans error: {ex}"
)
utils.logger.error(f"[BilibiliCrawler.get_fans] get creator_id: {creator_id} fans error: {ex}")
except Exception as e:
utils.logger.error(
f"[BilibiliCrawler.get_fans] may be been blocked, err:{e}"
)
utils.logger.error(f"[BilibiliCrawler.get_fans] may be been blocked, err:{e}")
async def get_followings(self, creator_info: Dict, semaphore: asyncio.Semaphore):
"""
@@ -769,9 +619,7 @@ class BilibiliCrawler(AbstractCrawler):
creator_id = creator_info["id"]
async with semaphore:
try:
utils.logger.info(
f"[BilibiliCrawler.get_followings] begin get creator_id: {creator_id} followings ..."
)
utils.logger.info(f"[BilibiliCrawler.get_followings] begin get creator_id: {creator_id} followings ...")
await self.bili_client.get_creator_all_followings(
creator_info=creator_info,
crawl_interval=random.random(),
@@ -780,13 +628,9 @@ class BilibiliCrawler(AbstractCrawler):
)
except DataFetchError as ex:
utils.logger.error(
f"[BilibiliCrawler.get_followings] get creator_id: {creator_id} followings error: {ex}"
)
utils.logger.error(f"[BilibiliCrawler.get_followings] get creator_id: {creator_id} followings error: {ex}")
except Exception as e:
utils.logger.error(
f"[BilibiliCrawler.get_followings] may be been blocked, err:{e}"
)
utils.logger.error(f"[BilibiliCrawler.get_followings] may be been blocked, err:{e}")
async def get_dynamics(self, creator_info: Dict, semaphore: asyncio.Semaphore):
"""
@@ -798,9 +642,7 @@ class BilibiliCrawler(AbstractCrawler):
creator_id = creator_info["id"]
async with semaphore:
try:
utils.logger.info(
f"[BilibiliCrawler.get_dynamics] begin get creator_id: {creator_id} dynamics ..."
)
utils.logger.info(f"[BilibiliCrawler.get_dynamics] begin get creator_id: {creator_id} dynamics ...")
await self.bili_client.get_creator_all_dynamics(
creator_info=creator_info,
crawl_interval=random.random(),
@@ -809,10 +651,6 @@ class BilibiliCrawler(AbstractCrawler):
)
except DataFetchError as ex:
utils.logger.error(
f"[BilibiliCrawler.get_dynamics] get creator_id: {creator_id} dynamics error: {ex}"
)
utils.logger.error(f"[BilibiliCrawler.get_dynamics] get creator_id: {creator_id} dynamics error: {ex}")
except Exception as e:
utils.logger.error(
f"[BilibiliCrawler.get_dynamics] may be been blocked, err:{e}"
)
utils.logger.error(f"[BilibiliCrawler.get_dynamics] may be been blocked, err:{e}")