Delete all translate func in all WebCrawlers

This commit is contained in:
unknown
2021-11-06 22:49:19 +08:00
parent 0c4df0130b
commit 41f4743149
8 changed files with 16 additions and 51 deletions

View File

@@ -57,8 +57,8 @@ def getCover_small(html):
result = str(html.xpath('//*[@id="waterfall"]/div/a/div[1]/img/@src')).strip(" ['']")
return result
def getTag(html):
x = html.xpath('/html/head/meta[@name="keywords"]/@content')[0].split(',')
return [translateTag_to_sc(i.strip()) for i in x[2:]] if len(x) > 2 else []
result = html.xpath('/html/head/meta[@name="keywords"]/@content')[0].split(',')
return result
def getSeries(html):
try:
result1 = str(html.xpath('//span[contains(text(),"系列:")]/../span[2]/text()')).strip(" ['']")

View File

@@ -76,11 +76,8 @@ def get_actor(lx: html.HtmlElement):
return r
def get_tag(lx: html.HtmlElement) -> str:
r = []
genres = lx.xpath("//span[@class='spec-content']/a[@itemprop='genre']/text()")
for g in genres:
r.append(translateTag_to_sc(str(g)))
return r
return genres
def get_extrafanart(lx: html.HtmlElement) -> str:
r = []

View File

@@ -123,25 +123,12 @@ def getTag(text):
result = html.xpath(
"//td[contains(text(),'ジャンル:')]/following-sibling::td/a/text()"
)
total = []
for i in result:
try:
total.append(translateTag_to_sc(i))
except:
pass
return total
return result
except:
result = html.xpath(
"//td[contains(text(),'ジャンル:')]/following-sibling::td/text()"
)
total = []
for i in result:
try:
total.append(translateTag_to_sc(i))
except:
pass
return total
return result
return result
def getCover(text, number):

View File

@@ -14,7 +14,7 @@ def getTitle_fc2com(htmlcode): #获取厂商
return result
def getActor_fc2com(htmlcode):
try:
html = etree.fromstring(htmlcode, etree.HTMLParser())
htmtml = etree.fromstring(htmlcode, etree.HTMLParser())
result = html.xpath('//*[@id="top"]/div[1]/section[1]/div/section/div[2]/ul/li[3]/a/text()')[0]
return result
except:
@@ -48,10 +48,7 @@ def getCover_fc2com(htmlcode2): #获取厂商 #
# return result
def getTag_fc2com(lx):
result = lx.xpath("//a[@class='tag tagTag']/text()")
tag = []
for i in result:
tag.append(ADC_function.translateTag_to_sc(i))
return tag
return result
def getYear_fc2com(release):
try:
result = re.search('\d{4}',release).group()

View File

@@ -72,8 +72,7 @@ def getSerise(html): #获取系列
return str(x[0]) if len(x) else ''
def getTag(html): # 获取标签
klist = html.xpath('/html/head/meta[@name="keywords"]/@content')[0].split(',')
taglist = [translateTag_to_sc(v) for v in klist[1:]]
return taglist
return klist
def getExtrafanart(htmlcode): # 获取剧照
html_pather = re.compile(r'<div id=\"sample-waterfall\">[\s\S]*?</div></a>\s*?</div>')
html = html_pather.search(htmlcode)

View File

@@ -108,23 +108,11 @@ def getRelease(a):
def getTag(html):
try:
result = html.xpath('//strong[contains(text(),"類別")]/../span/a/text()')
total = []
for i in result:
try:
total.append(translateTag_to_sc(i))
except:
pass
return total
return result
except:
result = html.xpath('//strong[contains(text(),"類別")]/../span/text()')
total = []
for i in result:
try:
total.append(translateTag_to_sc(i))
except:
pass
return total
return result
def getCover_small(html, index=0):
# same issue mentioned below,

View File

@@ -65,13 +65,7 @@ def getTag(a):
result2 = str(html.xpath('//th[contains(text(),"ジャンル:")]/../td/text()')).strip(" ['']").strip('\\n ').strip(
'\\n')
result = str(result1 + result2).strip('+').replace("', '\\n",",").replace("', '","").replace('"','').replace(',,','').split(',')
total = []
for i in result:
try:
total.append(translateTag_to_sc(i))
except:
pass
return total
return result
def getCover(htmlcode):
html = etree.fromstring(htmlcode, etree.HTMLParser())
result = str(html.xpath('//*[@id="EnlargeImage"]/@href')).strip(" ['']")

View File

@@ -90,8 +90,11 @@ def getRelease(html):
def getTag(html):
x = html.xpath('//span[@class="koumoku" and text()="ジャンル"]/../a[starts-with(@href,"/avod/genre/")]/text()')
return [translateTag_to_sc(i.strip()) for i in x if len(i.strip())] if len(x) and len(x[0]) else []
result = html.xpath('//span[@class="koumoku" and text()="ジャンル"]/../a[starts-with(@href,"/avod/genre/")]/text()')
total = []
for i in result:
total.append(i.replace("\n","").replace("\t",""))
return total
def getCover_small(html, index=0):