jiazhizhong/MediaCrawler
1
0
Fork 0
mirror of https://github.com/NanmiCoder/MediaCrawler.git synced 2026-06-08 10:57:26 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat: 增加搜索词来源渠道

Browse Source
This commit is contained in:
Relakkes
2024-08-23 08:29:24 +08:00
parent d3c5111985
commit c70bd9e071
15 changed files with 37 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
media_platform/tieba/core.py
View File

@@ -14,7 +14,7 @@ from proxy.proxy_ip_pool import IpInfoModel, create_ip_pool
from store import tieba as tieba_store
from tools import utils
from tools.crawler_util import format_proxy_info
from var import crawler_type_var
from var import crawler_type_var, source_keyword_var
from .client import BaiduTieBaClient
from .field import SearchNoteType, SearchSortType
@@ -74,6 +74,7 @@ class TieBaCrawler(AbstractCrawler):
config.CRAWLER_MAX_NOTES_COUNT = tieba_limit_count
start_page = config.START_PAGE
for keyword in config.KEYWORDS.split(","):
source_keyword_var.set(keyword)
utils.logger.info(f"[BaiduTieBaCrawler.search] Current search keyword: {keyword}")
page = 1
while (page - start_page + 1) * tieba_limit_count <= config.CRAWLER_MAX_NOTES_COUNT: