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

@@ -74,9 +74,8 @@ class Dlsite(Parser):
def getOutline(self, htmltree):
total = []
result = self.getTreeAll(htmltree, self.expr_outline)
for i in result:
total.append(i.strip('\r\n'))
return str(total).strip(" ['']").replace("', '', '",r'\n').replace("', '",r'\n').strip(", '', '")
total = [ x.strip() for x in result if x.strip()]
return '\n'.join(total)
def getRelease(self, htmltree):
return super().getRelease(htmltree).replace('','-').replace('','-').replace('','')
@@ -84,9 +83,6 @@ class Dlsite(Parser):
def getCover(self, htmltree):
return 'https:' + super().getCover(htmltree).replace('.webp', '.jpg')
def getTags(self, htmltree):
return self.getTreeAll(htmltree, self.expr_tags)
def getExtrafanart(self, htmltree):
try:
result = []