add mgstage film actor's thumb from seeaawiki_av_neme

AVDC_Main.py

@@ -1013,7 +1013,10 @@ def thumbDownload(self, json_data, path, naming_rule, Config, filepath, failed_f
             return
         i = 1
         while i <= int(Config['proxy']['retry']):
-            self.DownloadFileWithFilename(json_data['cover'], thumb_name, path, Config, filepath,
+            download_url = json_data['cover']
+            if  "largeImage" in json_data.keys() and len(json_data['largeImage']) > 0:
+                download_url = json_data['largeImage']  # mgstage 封面下载大图
+            self.DownloadFileWithFilename(download_url, thumb_name, path, Config, filepath,
                                           failed_folder)
             if not check_pic(path + '/' + thumb_name):
                 print('[!]Image Download Failed! Trying again. ' + str(i) + '/' + Config['proxy']['retry'])
@@ -1024,7 +1027,28 @@ def thumbDownload(self, json_data, path, naming_rule, Config, filepath, failed_f
             self.add_text_main('[+]Thumb Downloaded!  ' + thumb_name)
         else:
             os.remove(path + '/' + thumb_name)
-            raise Exception("The Size of Thumb is Error! Deleted " + thumb_name + '!')
+            raise Exception("The p of Thumb is Error! Deleted " + thumb_name + '!')
+    # ========================================================================下载poster缩略图
+    def posterDownload(self, json_data, path, naming_rule, Config, filepath, failed_folder):
+        poster_name = naming_rule + '-poster.jpg'
+        if os.path.exists(path + '/' + poster_name):
+            self.add_text_main('[+]Poseter Existed!     ' + poster_name)
+            return
+        i = 1
+        while i <= int(Config['proxy']['retry']):
+            download_url = json_data['cover']
+            self.DownloadFileWithFilename(download_url, poster_name, path, Config, filepath,
+                                          failed_folder)
+            if not check_pic(path + '/' + poster_name):
+                print('[!]Image Download Failed! Trying again. ' + str(i) + '/' + Config['proxy']['retry'])
+                i = i + 1
+            else:
+                break
+        if check_pic(path + '/' + poster_name):
+            self.add_text_main('[+]Poster Downloaded!  ' + poster_name)
+        else:
+            os.remove(path + '/' + poster_name)
+            raise Exception("The Size of Poster is Error! Deleted " + poster_name + '!')
 
     def deletethumb(self,path, naming_rule):
         try:
@@ -1539,6 +1563,8 @@ def Core_Main(self, filepath, number, mode, count):
             # imagecut 0 判断人脸位置裁剪缩略图为封面，1 裁剪右半面，3 下载小封面
             self.thumbDownload(json_data, path, naming_rule, Config, filepath, failed_folder)
             if self.Ui.checkBox_download_poster.isChecked():
+                if "largeImage" in json_data.keys() and len(json_data['largeImage']) > 0: ## 如果自带大封面了，直接下载小封面
+                   self.posterDownload(json_data, path, naming_rule, Config, filepath, failed_folder)
                 if self.smallCoverDownload(path, naming_rule, json_data, Config, filepath,
                                            failed_folder) == 'small_cover_error':  # 下载小封面
                     json_data['imagecut'] = 0

Function/Function.py

@@ -227,6 +227,7 @@ def getDataFromJSON(file_number, config, mode):  # 从JSON返回元数据
     number = json_data['number']
     actor_list = str(json_data['actor']).strip("[ ]").replace("'", '').split(',')  # 字符串转列表
     release = json_data['release']
+    outline = json_data['outline']
     try:
         cover_small = json_data['cover_small']
     except:
@@ -249,6 +250,8 @@ def getDataFromJSON(file_number, config, mode):  # 从JSON返回元数据
     title = title.replace(' ', '.')
     title = title.replace('【', '')
     title = title.replace('】', '')
+    title = title.replace('&', '')
+    outline = outline.replace('&', '')
     release = release.replace('/', '-')
     tmpArr = cover_small.split(',')
     if len(tmpArr) > 0:
@@ -272,6 +275,7 @@ def getDataFromJSON(file_number, config, mode):  # 从JSON返回元数据
     json_data['naming_media'] = naming_media
     json_data['naming_file'] = naming_file
     json_data['folder_name'] = folder_name
+    json_data['outline'] = outline
     return json_data
 
 

Function/getHtml.py

@@ -16,7 +16,7 @@ def get_config():
 
 
 # ========================================================================网页请求
-def get_html(url, cookies=None):
+def get_html(url, cookies=None,encode='utf-8'):
     config = get_config()
     retry_count = 0
     proxy = ''
@@ -37,14 +37,14 @@ def get_html(url, cookies=None):
                     'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
                                   'Chrome/60.0.3100.0 Safari/537.36'}
                 getweb = requests.get(str(url), headers=headers, timeout=timeout, proxies=proxies, cookies=cookies)
-                getweb.encoding = 'utf-8'
+                getweb.encoding = encode
                 return getweb.text
             else:
                 headers = {
                     'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) '
                                   'Chrome/68.0.3440.106 Safari/537.36'}
                 getweb = requests.get(str(url), headers=headers, timeout=timeout, cookies=cookies)
-                getweb.encoding = 'utf-8'
+                getweb.encoding = encode
                 return getweb.text
         except Exception as error_info:
             i += 1

Getter/jav321.py

@@ -2,7 +2,7 @@
 from lxml import etree
 import json
 from Function.getHtml import post_html
-
+from Getter.seesaawiki_av_neme import  getActorFromSeesaawiki
 
 def getActorPhoto(actor):
     data = {}
@@ -132,6 +132,11 @@ def main(number, isuncensored=False):
             'website': getWebsite(detail_page),
             'source': 'jav321.py',
         }
+        wikiActor = getActorFromSeesaawiki(number, dic)
+        acotrList = dic['actor'].split(',')
+        acotrList.extend(wikiActor['actor'])
+        dic['actor'] = ','.join(acotrList)
+        dic['actor_photo'] ={**dic['actor_photo'],**wikiActor['actor_photo']}
     except TimeoutError:
         dic = {
             'title': '',

Getter/mgstage.py

@@ -2,7 +2,7 @@
 from lxml import etree
 import json
 from Function.getHtml import get_html
-
+from Getter.seesaawiki_av_neme import  getActorFromSeesaawiki
 
 def getTitle(htmlcode):
     try:
@@ -107,6 +107,11 @@ def getOutline(htmlcode):
 def getScore(htmlcode):
     return str(re.findall(r'5点満点中 (\S+)点', htmlcode)).strip(" ['']")
 
+def getLargeImage(htmlcode):
+    html = etree.fromstring(htmlcode, etree.HTMLParser())
+    result = str(html.xpath('//*[@id="EnlargeImage"]/@href')).strip(" ['']")
+    return result
+
 
 def main(number):
     try:
@@ -128,7 +133,7 @@ def main(number):
             'release': getRelease(htmlcode).strip(','),
             'number': getNum(htmlcode).strip(','),
             'cover': getCover(htmlcode).strip(','),
-            'extrafanart': getExtraFanart(htmlcode).strip(','),
+            'extrafanart': getExtraFanart(htmlcode),
             'imagecut': 0,
             'tag': getTag(htmlcode).strip(','),
             'series': getSeries(htmlcode).strip(','),
@@ -137,7 +142,13 @@ def main(number):
             'director': '',
             'website': 'https://www.mgstage.com/product/product_detail/' + str(number) + '/',
             'source': 'mgstage.py',
+            'largeImage':getLargeImage(htmlcode).strip(',')
         }
+        wikiActor = getActorFromSeesaawiki(number, dic)
+        acotrList = dic['actor'].split(',')
+        acotrList.extend(wikiActor['actor'])
+        dic['actor'] = ','.join(acotrList)
+        dic['actor_photo'] ={**dic['actor_photo'],**wikiActor['actor_photo']}
     except TimeoutError:
         dic = {
             'title': '',

Getter/seesaawiki_av_neme.py

@@ -0,0 +1,47 @@
+import re
+from lxml import etree
+import json
+from Function.getHtml import get_html
+
+def getActorFromSeesaawiki(number, dic):
+    global localDic
+    localDic=dic.copy()
+    return getActor(number)
+
+def getActor(number):
+    wiki_html = get_html('https://seesaawiki.jp/av_neme/search?keywords=' + str(number),"","EUC-JP")
+    html = etree.fromstring(wiki_html, etree.HTMLParser())
+    result = html.xpath('//*[@id="page-body-inner"]//h3//a')
+    hrefs = html.xpath('//*[@id="page-body-inner"]//h3//a/@href')
+    result = list(filter(filterActor, result))
+    actors = []
+    actorPhotoDic = {}
+    for actor in result:
+        actors.append(actor.text)
+        photo = getActorPhoto(actor.text, actor.attrib['href'])
+        p2 = {actor.text: photo}
+        actorPhotoDic.update(p2)
+    dic = {
+        'actor': actors,
+        'actor_photo':actorPhotoDic
+    }   
+    return dic
+
+def getActorPhoto(actor, href):
+    print(href)
+    actor_html=get_html(href,"","EUC-JP")
+    html = etree.fromstring(actor_html, etree.HTMLParser())
+    p = str(html.xpath('//*[@id="content_block_1-body"]/a/img/@src')).strip(" ['']")
+    return p
+
+def stripActor(actor):
+    actor = actor.strip().strip("'")
+    return actor
+def filterActor(actor):
+    print(localDic)
+    if "年" in actor.text:
+        return False
+    if  actor.text ==localDic['series']:  
+        return False
+    return True
+