From f8dc05a38bad656a5d5ed186ea84ad0cce2ebc43 Mon Sep 17 00:00:00 2001
From: lededev <lededev@noreplay.github.com>
Date: Tue, 12 Oct 2021 11:28:17 +0800
Subject: [PATCH] improve javbus and javdb outline source

---
 ADC_function.py      |  2 +-
 WebCrawler/javbus.py | 12 +++++++++++-
 WebCrawler/javdb.py  |  1 -
 WebCrawler/xcity.py  | 13 ++++++++-----
 4 files changed, 20 insertions(+), 8 deletions(-)

diff --git a/ADC_function.py b/ADC_function.py
index 4480852..ed428bd 100755
--- a/ADC_function.py
+++ b/ADC_function.py
@@ -2,7 +2,7 @@ from os import replace
 import requests
 import hashlib
 from pathlib import Path
-#import secrets
+import secrets
 import os.path
 import uuid
 import json
diff --git a/WebCrawler/javbus.py b/WebCrawler/javbus.py
index c2ff11e..e739424 100644
--- a/WebCrawler/javbus.py
+++ b/WebCrawler/javbus.py
@@ -93,8 +93,12 @@ def getOutline0(number):  #获取剧情介绍 airav.wiki站点404，函数暂时
     return ''
 def getOutline(number):  #获取剧情介绍 从avno1.cc取得
     try:
+        url = 'http://www.avno1.cc/cn/' + secrets.choice(['usercenter.php?item=' +
+                secrets.choice(['pay_support', 'qa', 'contact', 'guide-vpn']),
+                '?top=1&cat=hd', '?top=1', '?cat=hd', 'porn', '?cat=jp', '?cat=us', 'recommend_category.php'
+        ]) # 随机选一个，避免网站httpd日志中单个ip的请求太过单一
         number_up = number.upper()
-        result, browser = get_html_by_form('http://www.avno1.cc/cn/usercenter.php?item=pay_support',
+        result, browser = get_html_by_form(url,
             form_select='div.wrapper > div.header > div.search > form',
             fields = {'kw' : number_up},
             return_type = 'browser')
@@ -107,6 +111,12 @@ def getOutline(number):  #获取剧情介绍 从avno1.cc取得
         return browser.page.select('div.type_movie > div > ul > li:nth-child(1) > div')[0]['data-description'].strip()
     except:
         pass
+    from WebCrawler.xcity import open_by_browser, getOutline as xcity_getOutline
+    try:
+        detail_html, browser = open_by_browser(number_up)
+        return xcity_getOutline(detail_html)
+    except:
+        pass
     return ''
 def getSerise(htmlcode):   #获取系列 已修改
     html = etree.fromstring(htmlcode, etree.HTMLParser())
diff --git a/WebCrawler/javdb.py b/WebCrawler/javdb.py
index 358682d..4b0d4c9 100755
--- a/WebCrawler/javdb.py
+++ b/WebCrawler/javdb.py
@@ -5,7 +5,6 @@ from lxml import etree
 import json
 from bs4 import BeautifulSoup
 from ADC_function import *
-import secrets
 # import sys
 # import io
 # sys.stdout = io.TextIOWrapper(sys.stdout.buffer, errors = 'replace', line_buffering = True)
diff --git a/WebCrawler/xcity.py b/WebCrawler/xcity.py
index 858dd54..4bbdec1 100644
--- a/WebCrawler/xcity.py
+++ b/WebCrawler/xcity.py
@@ -181,11 +181,10 @@ def getExtrafanart(htmlcode):  # 获取剧照
             return s
     return ''
 
-def main(number):
-    try:
+def open_by_browser(number):
         xcity_number = number.replace('-','')
         query_result, browser = get_html_by_form(
-            'https://xcity.jp/about/',
+            'https://xcity.jp/' + secrets.choice(['about/','sitemap/','policy/','law/','help/','main/']),
             fields = {'q' : xcity_number.lower()},
             return_type = 'browser')
         if not query_result or not query_result.ok:
@@ -193,12 +192,16 @@ def main(number):
         result = browser.follow_link(browser.links('avod\/detail')[0])
         if not result.ok:
             raise ValueError("xcity.py: detail page not found")
-        detail_page = str(browser.page)
+        return str(browser.page), browser
+
+def main(number):
+    try:
+        detail_page, browser = open_by_browser(number)
         url = browser.url
         newnum = getNum(detail_page).upper()
         number_up = number.upper()
         if newnum != number_up:
-            if newnum == xcity_number.upper():
+            if newnum == number.replace('-','').upper():
                 newnum = number_up
             else:
                 raise ValueError("xcity.py: number not found")