Merge pull request #636 from lededev/double-exception

bugfix

AV_Data_Capture.py

@@ -474,18 +474,11 @@ def main():
         check_update(version)
 
     # Download Mapping Table, parallel version
-    down_map_tab = []
-    actor_xml = Path.home() / '.local' / 'share' / 'avdc' / 'mapping_actor.xml'
-    if not actor_xml.exists():
-        down_map_tab.append((
-            "https://raw.githubusercontent.com/yoshiko2/AV_Data_Capture/master/MappingTable/mapping_actor.xml",
-            actor_xml))
-    info_xml = Path.home() / '.local' / 'share' / 'avdc' / 'mapping_info.xml'
-    if not info_xml.exists():
-        down_map_tab.append((
-            "https://raw.githubusercontent.com/yoshiko2/AV_Data_Capture/master/MappingTable/mapping_info.xml",
-            info_xml))
-    res = parallel_download_files(down_map_tab)
+    def fmd(f):
+        return ('https://raw.githubusercontent.com/yoshiko2/AV_Data_Capture/master/MappingTable/' + f,
+            Path.home() / '.local' / 'share' / 'avdc' / f)
+    map_tab = (fmd('mapping_actor.xml'), fmd('mapping_info.xml'), fmd('c_number.json'))
+    res = parallel_download_files(((k, v) for k, v in map_tab if not v.exists()))
     for i, fp in enumerate(res, start=1):
         if fp and len(fp):
             print(f"[+] [{i}/{len(res)}] Mapping Table Downloaded to {fp}")

WebCrawler/avsox.py

@@ -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):
-    result = html.xpath('/html/head/meta[@name="keywords"]/@content')[0].split(',')
-    return result
+    x = html.xpath('/html/head/meta[@name="keywords"]/@content')[0].split(',')
+    return [i.strip() for i in x[2:]]  if len(x) > 2 else []
 def getSeries(html):
     try:
         result1 = str(html.xpath('//span[contains(text(),"系列:")]/../span[2]/text()')).strip(" ['']")

WebCrawler/fc2.py

@@ -14,7 +14,7 @@ def getTitle_fc2com(htmlcode): #获取厂商
     return result
 def getActor_fc2com(htmlcode):
     try:
-        htmtml = etree.fromstring(htmlcode, etree.HTMLParser())
+        html = 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:

WebCrawler/javbus.py

@@ -72,7 +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(',')
-    return klist
+    return klist[1:]
 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)

WebCrawler/javlib.py

@@ -34,10 +34,10 @@ def main(number: str):
     )
     soup = BeautifulSoup(result.text, "html.parser")
     lx = html.fromstring(str(soup))
-    
+
     fanhao_pather = re.compile(r'<a href=".*?".*?><div class="id">(.*?)</div>')
     fanhao = fanhao_pather.findall(result.text)
-    
+
     if "/?v=jav" in result.url:
         dic = {
             "title": get_title(lx, soup),