storyline:add data source airavwiki

WebCrawler/javbus.py

@@ -5,6 +5,7 @@ from lxml import etree#need install
 import json
 from ADC_function import *
 from WebCrawler.storyline import getStoryline
+import inspect
 
 def getActorPhoto(html):
     actors = html.xpath('//div[@class="star-name"]/a')
@@ -60,6 +61,8 @@ def getCID(html):
     result = re.sub('/.*?.jpg','',string)
     return result
 def getOutline(number, title):  #获取剧情介绍 多进程并发查询
+    if any(caller for caller in inspect.stack() if os.path.basename(caller.filename) == 'airav.py'):
+        return ''   # 从airav.py过来的调用不计算outline直接返回，避免重复抓取数据拖慢处理速度
     return getStoryline(number,title)
 def getSeriseJa(html):
     x = html.xpath('//span[contains(text(),"シリーズ:")]/../a/text()')

WebCrawler/storyline.py

@@ -10,7 +10,7 @@ from difflib import SequenceMatcher
 from unicodedata import category
 from number_parser import is_uncensored
 
-G_registered_storyline_site = {"airav", "avno1", "xcity", "amazon", "58avgo"}
+G_registered_storyline_site = {"airavwiki", "airav", "avno1", "xcity", "amazon", "58avgo"}
 
 G_mode_txt = ('顺序执行','线程池','进程池')
 
@@ -83,6 +83,8 @@ def _getStoryline_mp(site, number, title, debug):
     storyline = None
     if not isinstance(site, str):
         return storyline
+    elif site == "airavwiki":
+        storyline = getStoryline_airavwiki(number, debug)
     elif site == "airav":
         storyline = getStoryline_airav(number, debug)
     elif site == "avno1":
@@ -113,9 +115,9 @@ def getStoryline_airav(number, debug):
         if not res.ok:
             raise ValueError(f"get_html_by_browser('{url}') failed")
         avs = browser.page.select_one('div.resultcontent > ul > li:nth-child(1) > div')
-        if number_up not in avs.select_one('a > h3').text.upper():
+        if number_up not in avs.a.h3.text.upper():
             raise ValueError("number not found")
-        detail_url = avs.select_one('a')['href']
+        detail_url = avs.a['href']
         res = browser.open_relative(detail_url)
         if not res.ok:
             raise ValueError(f"browser.open_relative('{detail_url}') failed")
@@ -132,6 +134,38 @@ def getStoryline_airav(number, debug):
     return None
 
 
+def getStoryline_airavwiki(number, debug):
+    try:
+        kwd = number[:6] if re.match(r'\d{6}[\-_]\d{2,3}', number) else number
+        url = f'https://cn.airav.wiki/?search={kwd}'
+        result, browser = get_html_by_browser(url, return_type='browser')
+        if not result.ok:
+            raise ValueError(f"get_html_by_browser('{url}','{number}') failed")
+        s = browser.page.select('div.row > div > div.videoList.row > div > a.d-block')
+        link = None
+        for a in s:
+            title = a.img['title']
+            if re.search(number, title, re.I):
+                link = a
+                break
+        if link is None:
+            raise ValueError("number not found")
+        result = browser.follow_link(link)
+        if not result.ok or not re.search(number, browser.url, re.I):
+            raise ValueError("detail page not found")
+        title = browser.page.select('head > title')[0].text.strip()
+        detail_number = str(re.findall('\[(.*?)]', title)[0])
+        if not re.search(number, detail_number, re.I):
+            raise ValueError("detail page number not match, got ->[{detail_number}]")
+        desc = browser.page.select_one('div.d-flex.videoDataBlock > div.synopsis > p').text.strip()
+        return desc
+    except Exception as e:
+        if debug:
+            print(f"[-]MP def getStoryline_airavwiki Error: {e}, number [{number}].")
+        pass
+    return ''
+
+
 def getStoryline_58avgo(number, debug):
     try:
         url = 'http://58avgo.com/cn/index.aspx' + secrets.choice([

config.ini

@@ -91,14 +91,14 @@ extrafanart_folder=extrafanart
 [storyline]
 ; website为javbus javdb avsox xcity carib时，site censored_site uncensored_site 为获取剧情简介信息的
 ; 可选数据源站点列表。列表内站点同时并发查询，取值优先级由冒号前的序号决定，从小到大，数字小的站点没数据才会采用后面站点获得的。
-; 其中airav avno1 58avgo是中文剧情简介，区别是airav只能查有码，avno1有码无码都能查，58avgo只能查无码或者
+; 其中airavwiki airav avno1 58avgo是中文剧情简介，区别是airav只能查有码，airavwiki avno1有码无码都能查，
-; 流出破解马赛克的影片(此功能没使用)。
+; 58avgo只能查无码或者流出破解马赛克的影片(此功能没使用)。
 ; xcity和amazon是日语的，由于amazon商城没有番号信息，选中对应DVD的准确率仅99.6%。如果三个列表全部为空则不查询，
 ; 设置成不查询可大幅提高刮削速度。
 ; site=
-site=3:avno1
+site=1:airavwiki,4:avno1
-censored_site=1:airav,4:xcity,5:amazon
+censored_site=2:airav,5:xcity,6:amazon
-uncensored_site=2:58avgo
+uncensored_site=3:58avgo
 ; 运行模式：0:顺序执行(最慢) 1:线程池(默认值) 2:进程池(启动开销比线程池大，并发站点越多越快)
 run_mode=1
 ; show_result剧情简介调试信息 0关闭 1简略 2详细(详细部分不记入日志)，剧情简介失效时可打开2查看原因