From 2ade44cd32fb995b6fa7930e7fc39c9e31a5500d Mon Sep 17 00:00:00 2001
From: Deng Zhou <553531284@qq.com>
Date: Sat, 22 Jan 2022 23:47:09 +0800
Subject: [PATCH 1/6] =?UTF-8?q?fix=20fanza=20=E5=89=A7=E7=85=A7?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 .gitignore          | 2 ++
 WebCrawler/fanza.py | 4 ++--
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/.gitignore b/.gitignore
index 95c3b73..09632a9 100644
--- a/.gitignore
+++ b/.gitignore
@@ -110,3 +110,5 @@ venv.bak/
 JAV_output/**/*
 failed/*
 .vscode/launch.json
+
+.idea
\ No newline at end of file
diff --git a/WebCrawler/fanza.py b/WebCrawler/fanza.py
index 00d8988..08ce923 100644
--- a/WebCrawler/fanza.py
+++ b/WebCrawler/fanza.py
@@ -197,7 +197,7 @@ def getSeries(text):
         return ""
 
 def getExtrafanart(htmlcode):  # 获取剧照
-    html_pather = re.compile(r'<div id=\"sample-image-block\"[\s\S]*?<br></div></div>')
+    html_pather = re.compile(r'<div id=\"sample-image-block\"[\s\S]*?<br></div>\n</div>')
     html = html_pather.search(htmlcode)
     if html:
         html = html.group()
@@ -314,4 +314,4 @@ def main_htmlcode(number):
 if __name__ == "__main__":
     # print(main("DV-1562"))
     # print(main("96fad1217"))
-    print(main("pred00251"))
+    print(main("h_173ghmt68"))

From 61de7863ede2452a4d9bab7004f8fadddac70c69 Mon Sep 17 00:00:00 2001
From: Deng Zhou <553531284@qq.com>
Date: Sat, 29 Jan 2022 21:36:16 +0800
Subject: [PATCH 2/6] =?UTF-8?q?=E5=B1=8F=E8=94=BDjavdb=20fix=20bug?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

---
 WebCrawler/javdb.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/WebCrawler/javdb.py b/WebCrawler/javdb.py
index 8a5de7a..3368430 100755
--- a/WebCrawler/javdb.py
+++ b/WebCrawler/javdb.py
@@ -139,7 +139,7 @@ def getCover_small(html, index=0):
 def getTrailer(htmlcode):  # 获取预告片
     video_pather = re.compile(r'<video id\=\".*?>\s*?<source src=\"(.*?)\"')
     video = video_pather.findall(htmlcode)
-    if video[0] != "":
+    if video and video[0] != "":
         if not 'https:' in video[0]:
             video_url = 'https:' + video[0]
         else:
@@ -179,7 +179,7 @@ def main(number):
     debug = config.getInstance().debug()
     for i in javdb_sites:
         javdb_sites[javdb_sites.index(i)] = "javdb" + i
-    javdb_sites.append("javdb")
+    #javdb_sites.append("javdb")
     try:
         # if re.search(r'[a-zA-Z]+\.\d{2}\.\d{2}\.\d{2}', number).group():
         #     pass
@@ -325,7 +325,7 @@ if __name__ == "__main__":
     # print(main('FC2-1174949')) # not found
     #print(main('MVSD-439'))
     # print(main('EHM0001')) # not found
-    print(main('FC2-2314275'))
+    print(main('032517_505'))
     # print(main('EBOD-646'))
     # print(main('LOVE-262'))
     #print(main('ABP-890'))

From f063383bb7271e94f33dd8375049fb23c2d7b767 Mon Sep 17 00:00:00 2001
From: Deng Zhou <553531284@qq.com>
Date: Fri, 29 Apr 2022 23:59:15 +0800
Subject: [PATCH 3/6] fix bug

---
 WebCrawler/javdb.py | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

diff --git a/WebCrawler/javdb.py b/WebCrawler/javdb.py
index 9168056..e1ec2a9 100755
--- a/WebCrawler/javdb.py
+++ b/WebCrawler/javdb.py
@@ -119,7 +119,7 @@ def getCover_small(html, index=0):
     # javdb sometime returns multiple results
     # DO NOT just get the firt one, get the one with correct index number
     try:
-        result = html.xpath("//div[@class='item-image fix-scale-cover']/img/@src")[index]
+        result = html.xpath("//*[@class='movie-list h cols-4']/div/a/div[contains(@class, 'cover')]/img/@src")[index]
         if not 'https' in result:
             result = 'https:' + result
         return result
@@ -237,12 +237,12 @@ def main(number):
         # javdb sometime returns multiple results,
         # and the first elememt maybe not the one we are looking for
         # iterate all candidates and find the match one
-        urls = html.xpath('//*[@id="videos"]/div/div/a/@href')
+        urls = html.xpath('//*[@class="movie-list h cols-4"]/div/a/@href')
         # 记录一下欧美的ids  ['Blacked','Blacked']
         if re.search(r'[a-zA-Z]+\.\d{2}\.\d{2}\.\d{2}', number):
             correct_url = urls[0]
         else:
-            ids = html.xpath('//*[@id="videos"]/div/div/a/div[contains(@class, "uid")]/text()')
+            ids = html.xpath('//*[@class="movie-list h cols-4"]/div/a/div[contains(@class, "video-title")]/strong/text()')
             try:
                 correct_url = urls[ids.index(number)]
             except:

From dd4afaf8819263502bd974d17aef546cf06a4c55 Mon Sep 17 00:00:00 2001
From: Deng Zhou <553531284@qq.com>
Date: Sat, 30 Apr 2022 00:03:16 +0800
Subject: [PATCH 4/6] fix bug

---
 WebCrawler/fanza.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/WebCrawler/fanza.py b/WebCrawler/fanza.py
index 4594987..622f837 100644
--- a/WebCrawler/fanza.py
+++ b/WebCrawler/fanza.py
@@ -67,7 +67,7 @@ def getOutline(html):
 
 
 def getExtrafanart(htmlcode):  # 获取剧照
-    html_pather = re.compile(r'<div id=\"sample-image-block\"[\s\S]*?<br></div></div>')
+    html_pather = re.compile(r'<div id=\"sample-image-block\"[\s\S]*?<br></div>\n</div>')
     html = html_pather.search(htmlcode)
     if html:
         html = html.group()

From 3813545e7ec342c74153036fba017538ac61a544 Mon Sep 17 00:00:00 2001
From: Deng Zhou <553531284@qq.com>
Date: Sat, 30 Apr 2022 00:15:16 +0800
Subject: [PATCH 5/6] temp

---
 WebCrawler/javdb.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/WebCrawler/javdb.py b/WebCrawler/javdb.py
index e1ec2a9..6cbe880 100755
--- a/WebCrawler/javdb.py
+++ b/WebCrawler/javdb.py
@@ -191,7 +191,7 @@ def main(number):
     debug = config.getInstance().debug()
     for i in javdb_sites:
         javdb_sites[javdb_sites.index(i)] = "javdb" + i
-    #javdb_sites.append("javdb")
+    javdb_sites.append("javdb")
     try:
         # if re.search(r'[a-zA-Z]+\.\d{2}\.\d{2}\.\d{2}', number).group():
         #     pass

From df9dae1fc29e366e9fd45fac9ccb6e847b8bed41 Mon Sep 17 00:00:00 2001
From: Deng Zhou <553531284@qq.com>
Date: Sat, 30 Apr 2022 00:54:04 +0800
Subject: [PATCH 6/6] imagecut

---
 WebCrawler/javdb.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/WebCrawler/javdb.py b/WebCrawler/javdb.py
index 6cbe880..5d8e8ea 100755
--- a/WebCrawler/javdb.py
+++ b/WebCrawler/javdb.py
@@ -260,8 +260,8 @@ def main(number):
 
         # etree.fromstring开销很大，最好只用一次，而它的xpath很快，比bs4 find/select快，可以多用
         lx = etree.fromstring(detail_page, etree.HTMLParser())
-        # no cut image by default
-        imagecut = 3
+        # 页面改版默认裁切
+        imagecut = 1
         # If gray image exists ,then replace with normal cover
         if re.search(r'[a-zA-Z]+\.\d{2}\.\d{2}\.\d{2}', number):
             cover_small = getCover_small(html)