jiazhizhong/MediaCrawler
1
0
Fork 0
mirror of https://github.com/NanmiCoder/MediaCrawler.git synced 2026-06-09 19:37:25 +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/kuaishou/core.py
View File

@@ -21,9 +21,6 @@ from .login import KuaishouLogin
class KuaishouCrawler(AbstractCrawler):
platform: str
login_type: str
crawler_type: str
context_page: Page
ks_client: KuaiShouClient
browser_context: BrowserContext
@@ -32,13 +29,6 @@ class KuaishouCrawler(AbstractCrawler):
self.index_url = "https://www.kuaishou.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:
@@ -64,7 +54,7 @@ class KuaishouCrawler(AbstractCrawler):
self.ks_client = await self.create_ks_client(httpx_proxy_format)
if not await self.ks_client.pong():
login_obj = KuaishouLogin(
login_type=self.login_type,
login_type=config.LOGIN_TYPE,
login_phone=httpx_proxy_format,
browser_context=self.browser_context,
context_page=self.context_page,
@@ -73,11 +63,11 @@ class KuaishouCrawler(AbstractCrawler):
await login_obj.begin()
await self.ks_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 notes 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:
@@ -90,8 +80,8 @@ class KuaishouCrawler(AbstractCrawler):
ks_limit_count = 20 # kuaishou limit page fixed value
if config.CRAWLER_MAX_NOTES_COUNT < ks_limit_count:
config.CRAWLER_MAX_NOTES_COUNT = ks_limit_count
start_page = self.start_page
for keyword in self.keyword.split(","):
start_page = config.START_PAGE
for keyword in config.KEYWORDS.split(","):
utils.logger.info(f"[KuaishouCrawler.search] Current search keyword: {keyword}")
page = 1
while (page - start_page + 1) * ks_limit_count <= config.CRAWLER_MAX_NOTES_COUNT:
@@ -238,7 +228,7 @@ class KuaishouCrawler(AbstractCrawler):
utils.logger.info("[KuaishouCrawler.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 % 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,