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

improve base config reading command line arg logic

Browse Source
This commit is contained in:
nelzomal
2024-06-09 09:35:52 +08:00
parent 3c7c678d7a
commit eace7d1750
15 changed files with 91 additions and 139 deletions
Download Patch File Download Diff File Expand all files Collapse all files

24
media_platform/bilibili/core.py
View File

@@ -26,9 +26,6 @@ from .login import BilibiliLogin
class BilibiliCrawler(AbstractCrawler):
platform: str
login_type: str
crawler_type: str
context_page: Page
bili_client: BilibiliClient
browser_context: BrowserContext
@@ -37,13 +34,6 @@ class BilibiliCrawler(AbstractCrawler):
self.index_url = "https://www.bilibili.com"
self.user_agent = utils.get_user_agent()
def init_config(self, platform: str, login_type: str, crawler_type: str, start_page: int, keyword: str):
self.platform = platform
self.login_type = login_type
self.crawler_type = crawler_type
self.start_page = start_page
self.keyword = keyword
async def start(self):
playwright_proxy_format, httpx_proxy_format = None, None
if config.ENABLE_IP_PROXY:
@@ -70,7 +60,7 @@ class BilibiliCrawler(AbstractCrawler):
self.bili_client = await self.create_bilibili_client(httpx_proxy_format)
if not await self.bili_client.pong():
login_obj = BilibiliLogin(
login_type=self.login_type,
login_type=config.LOGIN_TYPE,
login_phone="", # your phone number
browser_context=self.browser_context,
context_page=self.context_page,
@@ -79,11 +69,11 @@ class BilibiliCrawler(AbstractCrawler):
await login_obj.begin()
await self.bili_client.update_cookies(browser_context=self.browser_context)
crawler_type_var.set(self.crawler_type)
if self.crawler_type == "search":
crawler_type_var.set(config.CRAWLER_TYPE)
if config.CRAWLER_TYPE == "search":
# Search for video and retrieve their comment information.
await self.search()
elif self.crawler_type == "detail":
elif config.CRAWLER_TYPE == "detail":
# Get the information and comments of the specified post
await self.get_specified_videos()
else:
@@ -101,8 +91,8 @@ class BilibiliCrawler(AbstractCrawler):
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(","):
start_page = config.START_PAGE # start page number
for keyword in config.KEYWORDS.split(","):
utils.logger.info(
f"[BilibiliCrawler.search] Current search keyword: {keyword}")
page = 1
@@ -271,7 +261,7 @@ class BilibiliCrawler(AbstractCrawler):
# 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 % self.platform) # type: ignore
config.USER_DATA_DIR % config.PLATFORM) # type: ignore
browser_context = await chromium.launch_persistent_context(
user_data_dir=user_data_dir,
accept_downloads=True,