Add crawler named gcolle.py

WebCrawler/__init__.py

@@ -24,6 +24,7 @@ from . import carib
 from . import fc2club
 from . import mv91
 from . import madou
+from . import gcolle
 
 
 def get_data_state(data: dict) -> bool:  # 元数据获取失败检测
@@ -62,7 +63,8 @@ def get_data_from_json(file_number, oCC):
         "carib": carib.main,
         "fc2club": fc2club.main,
         "mv91": mv91.main,
-        "madou": madou.main
+        "madou": madou.main,
+        "gcolle": gcolle.main,
     }
 
     conf = config.getInstance()
@@ -75,6 +77,8 @@ def get_data_from_json(file_number, oCC):
         if "carib" in sources and (re.match(r"^\d{6}-\d{3}", file_number)
         ):
             sources.insert(0, sources.pop(sources.index("carib")))
+        elif "gcolle" in sources and (re.search("\d{6}", file_number)):
+            sources.insert(0, sources.pop(sources.index("gcolle")))
         elif re.match(r"^\d{5,}", file_number) or "heyzo" in lo_file_number:
             if "javdb" in sources:
                 sources.insert(0, sources.pop(sources.index("javdb")))

WebCrawler/gcolle.py

@@ -0,0 +1,99 @@
+import sys
+sys.path.append('../')
+
+from ADC_function import *
+from lxml import etree
+from requests_html import HTMLSession
+
+class Crawler:
+    def __init__(self,htmlcode):
+        self.html = etree.HTML(htmlcode)
+
+    def getString(self,_xpath):
+        if _xpath == "":
+            return ""
+        result = self.html.xpath(_xpath)
+        try:
+            return result[0]
+        except:
+            return ""
+
+    def getStrings(self,_xpath):
+        result = self.html.xpath(_xpath)
+        try:
+            return result
+        except:
+            return ""
+
+    def getOutline(self,_xpath):
+        result = self.html.xpath(_xpath)
+        try:
+            return "\n".join(result)
+        except:
+            return ""
+
+def main(number):
+    config_file = config.getInstance()
+    browser = HTMLSession()
+
+    number = number.upper().replace('GCOLLE-','')
+
+    htmlcode = get_html_requests_html(browser,'https://gcolle.net/product_info.php/products_id/' + number)
+    html = etree.HTML(htmlcode)
+    # R18 countinue
+    htmlcode = get_html_requests_html(browser,html.xpath('//*[@id="main_content"]/table[1]/tbody/tr/td[2]/table/tbody/tr/td/h4/a[2]/@href')[0])
+    gcolle_crawler = Crawler(htmlcode)
+
+    number_html = gcolle_crawler.getString('//td[contains(text(),"商品番号")]/../td[2]/text()')
+    if number != number_html:
+        if config_file.debug():
+            print('[!]gcolle.py: number not match')
+        return {'title':''}
+
+    # get extrafanart url
+    if len(gcolle_crawler.getStrings('//*[@id="cart_quantity"]/table/tr[3]/td/div/img/@src')) == 0:
+        extrafanart = gcolle_crawler.getStrings('//*[@id="cart_quantity"]/table/tr[3]/td/div/a/img/@src')
+    else:
+        extrafanart = gcolle_crawler.getStrings('//*[@id="cart_quantity"]/table/tr[3]/td/div/img/@src')
+    # Add "https:" in each extrafanart url
+    for i in range(len(extrafanart)):
+        extrafanart[i] = 'https:' + extrafanart[i]
+
+    dic = {
+        "title":      gcolle_crawler.getString('//*[@id="cart_quantity"]/table/tr[1]/td/h1/text()'),
+        "studio":     gcolle_crawler.getString('//td[contains(text(),"アップロード会員名")]/b/text()'),
+        "year":       re.findall('\d{4}',gcolle_crawler.getString('//td[contains(text(),"商品登録日")]/../td[2]/time/@datetime'))[0],
+        "outline":    gcolle_crawler.getOutline('//*[@id="cart_quantity"]/table/tr[3]/td/p/text()'),
+        "runtime":    '',
+        "director":   gcolle_crawler.getString('//td[contains(text(),"アップロード会員名")]/b/text()'),
+        "actor":      gcolle_crawler.getString('//td[contains(text(),"アップロード会員名")]/b/text()'),
+        "release":    re.findall('\d{4}-\d{2}-\d{2}',gcolle_crawler.getString('//td[contains(text(),"商品登録日")]/../td[2]/time/@datetime'))[0],
+        "number":     "GCOLLE-" + str(number_html),
+        "cover":      "https:" + gcolle_crawler.getString('//*[@id="cart_quantity"]/table/tr[3]/td/table/tr/td/a/@href'),
+        "thumb":      "https:" + gcolle_crawler.getString('//*[@id="cart_quantity"]/table/tr[3]/td/table/tr/td/a/@href'),
+        "trailer":    '',
+        "actor_photo":'',
+        "imagecut":   4, # 该值为4时同时也是有码影片 也用人脸识别裁剪封面
+        "tag":        gcolle_crawler.getStrings('//*[@id="cart_quantity"]/table/tr[4]/td/a/text()'),
+        "extrafanart":extrafanart,
+        "label":      gcolle_crawler.getString('//td[contains(text(),"アップロード会員名")]/b/text()'),
+        "website":    'https://gcolle.net/product_info.php/products_id/' + number,
+        "source":     'gcolle.py',
+        "series":     gcolle_crawler.getString('//td[contains(text(),"アップロード会員名")]/b/text()'),
+        '无码': False,
+    }
+    # for k,v in dic.items():
+    #     if k == 'outline':
+    #         print(k,len(v))
+    #     else:
+    #         print(k,v)
+    # print('===============================================================')
+    return dic
+
+if __name__ == '__main__':
+    main('840724')
+    main('840386')
+    main('838671')
+    main('814179')
+    main('834255')
+    main('814179')