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

14
scrapinglib/dlsite.py
View File

@@ -36,22 +36,22 @@ class Dlsite(Parser):
else:
self.detailurl = f'https://www.dlsite.com/maniax/fsr/=/language/jp/sex_category/male/keyword/{number}/order/trend/work_type_category/movie'
htmltree = self.getHtmlTree(self.detailurl)
search_result = self.getAll(htmltree, '//*[@id="search_result_img_box"]/li[1]/dl/dd[2]/div[2]/a/@href')
search_result = self.getTreeAll(htmltree, '//*[@id="search_result_img_box"]/li[1]/dl/dd[2]/div[2]/a/@href')
if len(search_result) == 0:
number = number.replace("THE ANIMATION", "").replace("he Animation", "").replace("t", "").replace("T","")
htmltree = self.getHtmlTree(f'https://www.dlsite.com/maniax/fsr/=/language/jp/sex_category/male/keyword/{number}/order/trend/work_type_category/movie')
search_result = self.getAll(htmltree, '//*[@id="search_result_img_box"]/li[1]/dl/dd[2]/div[2]/a/@href')
search_result = self.getTreeAll(htmltree, '//*[@id="search_result_img_box"]/li[1]/dl/dd[2]/div[2]/a/@href')
if len(search_result) == 0:
if "～" in number:
number = number.replace("～","〜")
elif "〜" in number:
number = number.replace("〜","～")
htmltree = self.getHtmlTree(f'https://www.dlsite.com/maniax/fsr/=/language/jp/sex_category/male/keyword/{number}/order/trend/work_type_category/movie')
search_result = self.getAll(htmltree, '//*[@id="search_result_img_box"]/li[1]/dl/dd[2]/div[2]/a/@href')
search_result = self.getTreeAll(htmltree, '//*[@id="search_result_img_box"]/li[1]/dl/dd[2]/div[2]/a/@href')
if len(search_result) == 0:
number = number.replace('上巻', '').replace('下巻', '').replace('前編', '').replace('後編', '')
htmltree = self.getHtmlTree(f'https://www.dlsite.com/maniax/fsr/=/language/jp/sex_category/male/keyword/{number}/order/trend/work_type_category/movie')
search_result = self.getAll(htmltree, '//*[@id="search_result_img_box"]/li[1]/dl/dd[2]/div[2]/a/@href')
search_result = self.getTreeAll(htmltree, '//*[@id="search_result_img_box"]/li[1]/dl/dd[2]/div[2]/a/@href')
self.detailurl = search_result[0]
htmltree = self.getHtmlTree(self.detailurl)
self.number = str(re.findall("\wJ\w+", self.detailurl)).strip(" [']")
@@ -71,7 +71,7 @@ class Dlsite(Parser):
def getOutline(self, htmltree):
total = []
result = self.getAll(htmltree, self.expr_outline)
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(", '', '")
@@ -83,12 +83,12 @@ class Dlsite(Parser):
return 'https:' + super().getCover(htmltree).replace('.webp', '.jpg')
def getTags(self, htmltree):
return self.getAll(htmltree, self.expr_tags)
return self.getTreeAll(htmltree, self.expr_tags)
def getExtrafanart(self, htmltree):
try:
result = []
for i in self.getAll(self.expr_extrafanart):
for i in self.getTreeAll(self.expr_extrafanart):
result.append("https:" + i)
except:
result = ''