bacow/AV_Data_Capture
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

update scrapinglib

Browse Source
This commit is contained in:
Mathhew
2022-06-13 10:00:41 +08:00
parent 8348fa167b
commit 4074dcd366
16 changed files with 100 additions and 100 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
scrapinglib/fanza.py
View File

@@ -68,9 +68,9 @@ class Fanza(Parser):
def getOutline(self, htmltree):
try:
result = self.getTreeIndex(htmltree, self.expr_outline).replace("\n", "")
result = self.getTreeElement(htmltree, self.expr_outline).replace("\n", "")
if result == '':
result = self.getTreeIndex(htmltree, self.expr_outline2).replace("\n", "")
result = self.getTreeElement(htmltree, self.expr_outline2).replace("\n", "")
return result
except:
return ''
@@ -98,13 +98,13 @@ class Fanza(Parser):
# return super().getCover(htmltree)
cover_number = self.fanza_hinban
try:
result = self.getTreeIndex(htmltree, '//*[@id="' + cover_number + '"]/@href')
result = self.getTreeElement(htmltree, '//*[@id="' + cover_number + '"]/@href')
except:
# sometimes fanza modify _ to \u0005f for image id
if "_" in cover_number:
cover_number = cover_number.replace("_", r"\u005f")
try:
result = self.getTreeIndex(htmltree, '//*[@id="' + cover_number + '"]/@href')
result = self.getTreeElement(htmltree, '//*[@id="' + cover_number + '"]/@href')
except:
# (TODO) handle more edge case
# print(html)