update scrapinglib

- 优化提取extrafanart,trailer等,直接使用xpath expr,不需要正则匹配
- 优化 getchu 获取cover方法,直接使用og标签信息
- 优化 www.getchu 识别 getchu-id 的资源
- 统一获取 tag 方法,返回值 list
This commit is contained in:
Mathhew
2022-06-15 14:23:49 +08:00
parent eed33408a8
commit 0dda035057
16 changed files with 107 additions and 218 deletions

View File

@@ -2,7 +2,7 @@
from lxml.html import HtmlElement
def getTreeElement(tree: HtmlElement, expr, index=0):
def getTreeElement(tree: HtmlElement, expr='', index=0):
""" 根据表达式从`xmltree`中获取匹配值,默认 index 为 0
:param tree (html.HtmlElement)
:param expr
@@ -16,16 +16,16 @@ def getTreeElement(tree: HtmlElement, expr, index=0):
except:
return ''
def getTreeAll(tree: HtmlElement, expr):
def getTreeAll(tree: HtmlElement, expr=''):
""" 根据表达式从`xmltree`中获取全部匹配值
:param tree (html.HtmlElement)
:param expr
:param index
"""
if expr == '':
return ''
return []
result = tree.xpath(expr)
try:
return result
except:
return ''
return []