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

update scrapinglib

Browse Source 
- 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
Download Patch File Download Diff File Expand all files Collapse all files

43
scrapinglib/jav321.py
View File

@@ -12,15 +12,15 @@ class Jav321(Parser):
expr_title = "/html/body/div[2]/div[1]/div[1]/div[1]/h3/text()"
expr_cover = "/html/body/div[2]/div[2]/div[1]/p/a/img/@src"
expr_outline = "/html/body/div[2]/div[1]/div[1]/div[2]/div[3]/div/text()"
# NOTE: 统一使用 xpath
expr_number = '//b[contains(text(),"品番")]/following-sibling::node()'
expr_actor = '//b[contains(text(),"出演者")]/following-sibling::a[starts-with(@href,"/star")]'
expr_label = '//b[contains(text(),"メーカー")]/following-sibling::a[starts-with(@href,"/company")]'
expr_tags = '//b[contains(text(),"ジャンル")]/following-sibling::a[starts-with(@href,"/genre")]'
expr_studio = '//b[contains(text(),"メーカー")]/following-sibling::a[starts-with(@href,"/company")]'
expr_actor = '//b[contains(text(),"出演者")]/following-sibling::a[starts-with(@href,"/star")]/text()'
expr_label = '//b[contains(text(),"メーカー")]/following-sibling::a[starts-with(@href,"/company")]/text()'
expr_tags = '//b[contains(text(),"ジャンル")]/following-sibling::a[starts-with(@href,"/genre")]/text()'
expr_studio = '//b[contains(text(),"メーカー")]/following-sibling::a[starts-with(@href,"/company")]/text()'
expr_release = '//b[contains(text(),"配信開始日")]/following-sibling::node()'
expr_runtime = '//b[contains(text(),"収録時間")]/following-sibling::node()'
# expr_series = '//b[contains(text(),"シリーズ")]'
expr_series = '//b[contains(text(),"シリーズ")]/following-sibling::node()'
expr_extrafanart = '//div[@class="col-md-3"]/div[@class="col-xs-12 col-md-12"]/p/a/img/@src'
def queryNumberUrl(self, number):
return 'https://www.jav321.com/search'
@@ -45,39 +45,8 @@ class Jav321(Parser):
else:
return ''
def getExtrafanart(self, htmltree):
html_pather = re.compile(r'<div class=\"col\-md\-3\"><div class=\"col\-xs\-12 col\-md\-12\">[\s\S]*?</script><script async src=\"\/\/adserver\.juicyads\.com/js/jads\.js\">')
html = html_pather.search(self.detailhtml)
if html:
html = html.group()
extrafanart_pather = re.compile(r'<img.*?src=\"(.*?)\"')
extrafanart_imgs = extrafanart_pather.findall(html)
if extrafanart_imgs:
return extrafanart_imgs
return ''
def getRelease(self, htmltree):
return super().getRelease(htmltree).split(": ")[1]
def getRuntime(self, htmltree):
return super().getRuntime(htmltree).split(": ")[1]
def parseElement(self, all):
if all:
ret = []
for si in all:
ret.append(si.text)
return ",".join(ret)
return ''
def getActors(self, htmltree):
return self.parseElement(super().getActors(htmltree))
def getLabel(self, htmltree):
return self.parseElement(self.getTreeAll(htmltree, self.expr_label))
def getTags(self, htmltree):
return self.parseElement(self.getTreeAll(htmltree, self.expr_tags))
def getStudio(self, htmltree):
return self.parseElement(self.getTreeAll(htmltree, self.expr_studio))