update

find_source/common/tools.py

@@ -3,7 +3,6 @@ import hashlib
 import re
 import time
 from collections import namedtuple
-from urllib.parse import urlparse, urljoin
 
 from lxml.html import HtmlElement, fromstring, tostring
 
@@ -36,21 +35,6 @@ def remove_node(node: HtmlElement):
         parent.remove(node)
 
 
-def text_search(text: str) -> SearchText:
-    """
-    中文检索
-
-    :param text: 文本
-    :return: 中文数量
-    """
-    if not text:
-        return SearchText(0)
-
-    results = re.findall('[\u4e00-\u9fa5]', text, re.S)
-    # 列表长度即是中文的字数
-    return SearchText(len(results))
-
-
 def verify_text(val: str):
     """检查数字、字母、中文的个数"""
     if val is None:
@@ -137,20 +121,3 @@ def delay_by_day(days, fmt="%Y-%m-%d %H:%M:%S"):
     _days = int(days)
     _current_now = datetime.datetime.now()
     return (_current_now + datetime.timedelta(days=_days)).strftime(fmt)
-
-
-def compliance_href(href: str):
-    if href in [None, ''] or re.match("^((https|http|ftp|rtsp|mms)?://|/\w+\\?)", href) is None:
-        return False
-    return True
-
-
-def is_href(href: str):
-    result = urlparse(href)
-    if all([len(result.scheme) == 0 and len(result.netloc) == 0]):
-        return False
-    return True
-
-
-def join_url(base, url):
-    return urljoin(base, url)