diff --git a/WebCrawler/javbus.py b/WebCrawler/javbus.py
index 2a5a303..5218016 100644
--- a/WebCrawler/javbus.py
+++ b/WebCrawler/javbus.py
@@ -88,7 +88,8 @@ def getUncensored(html):
return bool(x)
def main_uncensored(number):
- htmlcode = get_html('https://www.javbus.com/ja/' + number)
+ w_number = number.replace('.', '-')
+ htmlcode = get_html('https://www.javbus.red/' + w_number)
if "
404 Page Not Found" in htmlcode:
raise Exception('404 page not found')
lx = etree.fromstring(htmlcode, etree.HTMLParser())
@@ -97,7 +98,7 @@ def main_uncensored(number):
'title': title,
'studio': getStudioJa(lx),
'year': getYear(lx),
- 'outline': getOutline(number, title),
+ 'outline': getOutline(w_number, title),
'runtime': getRuntime(lx),
'director': getDirectorJa(lx),
'actor': getActor(lx),
@@ -109,10 +110,10 @@ def main_uncensored(number):
'label': getSeriseJa(lx),
'imagecut': 0,
# 'actor_photo': '',
- 'website': 'https://www.javbus.com/ja/' + number,
+ 'website': 'https://www.javbus.red/' + w_number,
'source': 'javbus.py',
'series': getSeriseJa(lx),
- '无码': getUncensored(lx)
+ '无码': True
}
js = json.dumps(dic, ensure_ascii=False, sort_keys=True, indent=4, separators=(',', ':'), ) # .encode('UTF-8')
return js
@@ -174,12 +175,13 @@ def main(number):
if __name__ == "__main__" :
config.G_conf_override['debug_mode:switch'] = True
- print(main('ABP-888'))
- print(main('ABP-960'))
- print(main('ADV-R0624')) # 404
- print(main('MMNT-010'))
- print(main('ipx-292'))
- print(main('CEMD-011'))
- print(main('CJOD-278'))
+ # print(main('ABP-888'))
+ # print(main('ABP-960'))
+ # print(main('ADV-R0624')) # 404
+ # print(main('MMNT-010'))
+ # print(main('ipx-292'))
+ # print(main('CEMD-011'))
+ # print(main('CJOD-278'))
+ print(main('BrazzersExxtra.21.02.01'))
print(main('100221_001'))
print(main('AVSW-061'))
diff --git a/WebCrawler/javdb.py b/WebCrawler/javdb.py
index 2d21e29..3dfff16 100755
--- a/WebCrawler/javdb.py
+++ b/WebCrawler/javdb.py
@@ -180,7 +180,8 @@ def getUserRating(html):
except:
return
def getUncensored(html):
- x = html.xpath('//strong[contains(text(),"類別")]/../span/a[contains(@href,"/tags/uncensored?")]')
+ x = html.xpath('//strong[contains(text(),"類別")]/../span/a[contains(@href,"/tags/uncensored?")'
+ ' or contains(@href,"/tags/western?")]')
return bool(x)
def main(number):
@@ -342,3 +343,4 @@ if __name__ == "__main__":
# print(main('EBOD-646'))
# print(main('LOVE-262'))
print(main('ABP-890'))
+ print(main('blacked.14.12.08'))