ada/CourseWork_IRFM
1
0
Fork 0
mirror of https://github.com/ada-dmitry/CourseWork_IRFM.git synced 2026-09-24 01:10:18 +00:00
Code Issues Packages Projects Releases Wiki Activity

Remove outdated documentation and improve comments in main and crawler modules

Browse Source
This commit is contained in:
Dmitry
2026-04-29 23:23:09 +03:00
parent 045fc41660
commit bf13d4d478
7 changed files with 2 additions and 625 deletions
Download Patch File Download Diff File Expand all files Collapse all files
modules/crawler.py
+1 -1
View File
@@ -11,7 +11,7 @@ START_URL = "https://www.consultant.ru/document/cons_doc_LAW_10699/" # Базо
FIRST_ARTICLE_URL = START_URL + "e8ecf933c52a85d9223094e0e7fbf52f0128d399/" # Первая статья (для детерминированности обхода)
ARTICLE_RE = re.compile(r"^\s*(?:УК РФ,?\s+)?Статья\s+\d+(?:\.\d+)?\.", re.IGNORECASE)
STRUCTURE_PREFIX_RE = re.compile(r"^\s*(?:\d+(?:\.\d+)*|[а-яё])[\.)]\s+", re.IGNORECASE)
STRUCTURE_PREFIX_RE = re.compile(r"^\s*(?:\d+(?:\.\d+)*|[а-яё])[\.)]\s+", re.IGNORECASE) # Строки, начинающиеся с нумерованного или буквенного маркера списка.
SPACE_RE = re.compile(r"[ \t\r\f\v]+")