修复bug，新增anidb数据库抓取程式

.gitignore

@@ -163,5 +163,5 @@ cython_debug/
 /auto_bangumi/const_dev.py
 /config/bangumi.json
 /auto_bangumi/tester.py
-/source/names.txt
+/resource/names.txt
 

.idea/Bangumi_Auto_Rename.iml

@@ -4,7 +4,7 @@
     <content url="file://$MODULE_DIR$">
       <sourceFolder url="file://$MODULE_DIR$/auto_bangumi" isTestSource="false" />
     </content>
-    <orderEntry type="jdk" jdkName="Python 3.10" jdkType="Python SDK" />
+    <orderEntry type="jdk" jdkName="Python 3.10 (np_veclib)" jdkType="Python SDK" />
     <orderEntry type="sourceFolder" forTests="false" />
   </component>
 </module>

.idea/misc.xml

@@ -1,4 +1,4 @@
 <?xml version="1.0" encoding="UTF-8"?>
 <project version="4">
-  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.10" project-jdk-type="Python SDK" />
+  <component name="ProjectRootManager" version="2" project-jdk-name="Python 3.10 (np_veclib)" project-jdk-type="Python SDK" />
 </project>

auto_bangumi/app.py

@@ -29,6 +29,7 @@ def load_data_file():
         if bangumi_data["data_version"] != settings.data_version or bangumi_data["rss_link"] != settings.rss_link:
             bangumi_data["bangumi_info"] = []
             bangumi_data["rss_link"] = settings.rss_link
+            logger.info("Rebuilding data information...")
     return bangumi_data
 
 

auto_bangumi/core/download_client.py

@@ -114,5 +114,13 @@ class DownloadClient:
 
 
 if __name__ == "__main__":
-    put = DownloadClient()
-    put.add_rules()
+    try:
+        from const_dev import DEV_SETTINGS
+    except ModuleNotFoundError:
+        logger.debug("Please copy `const_dev.py` to `const_dev.py` to use custom settings")
+    settings.init(DEV_SETTINGS)
+    client = getClient()
+    try:
+        client.rss_remove_item(item_path="Mikan_RSS")
+    except ConflictError:
+        logger.info("No feed exists, start adding feed.")

auto_bangumi/core/eps_complete.py

@@ -33,7 +33,7 @@ class FullSeasonGet:
             season = ""
         else:
             season = self.season
-        search_str = re.sub(r"[& ]", "+",
+        search_str = re.sub(r"[\W_]", "+",
                             f"{self.group} {self.bangumi_name} {season} {self.subtitle} {self.source} {self.dpi}")
         season = requests.get(
             f"https://mikanani.me/RSS/Search?searchstr={search_str}"

auto_bangumi/downloader/qb_downloader.py

@@ -63,7 +63,18 @@ class QbDownloader:
             self._client.rss_remove_item(item_path)
         except Conflict409Error as e:
             logger.exception(e)
+            logger.info("Add new RSS")
             raise ConflictError()
 
     def rss_set_rule(self, rule_name, rule_def):
         self._client.rss_set_rule(rule_name, rule_def)
+
+
+if __name__ == "__main__":
+    try:
+        from const_dev import DEV_SETTINGS
+    except ModuleNotFoundError:
+        logger.debug("Please copy `const_dev.py` to `const_dev.py` to use custom settings")
+    settings.init(DEV_SETTINGS)
+    client = QbDownloader(settings.host_ip, settings.user_name, settings.password)
+    client.rss_remove_item("Mikan_RSS")

requirements.txt

@@ -2,5 +2,4 @@ qbittorrent-api
 bs4
 requests
 lxml
-zhconv
 

resource/anidb.py

@@ -0,0 +1,76 @@
+#! /usr/bin/python
+import re
+import requests
+from bs4 import BeautifulSoup
+from utils import json_config
+
+header = {
+    'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) ApplewebKit/537.36 (KHtml, like Gecko) Chrome/80.0.3987.163 Safari/537.36',
+}
+
+
+def get_html(url):
+    requests.adapters.DEFAULT_RETRIES = 5  # 增加重连次数
+    s = requests.session()
+    s.keep_alive = False  # 关闭多余连接
+    html = s.get(url=url, headers=header).text
+    print("get html success")
+    return html
+
+
+def get_list(year, season):
+    season = ["spring", "summer", "autumn", "winter"][season - 1]
+    url = "https://anidb.net/anime/season/%s/%s/" % (year, season)
+    html = get_html(url)
+    ids = re.findall("<a href=\"/anime/(\d+)\"><picture>", html)
+    return ids
+
+
+def get_title(id):
+    url = "https://anidb.net/anime/%s" % id
+    soup = BeautifulSoup(get_html(url), "lxml")
+    titles = soup.find("div", id="tab_2_pane")
+    g = titles.findAll("th")
+    v = titles.findAll("td")
+    t_dic = {
+        "id": id,
+        "main": None,
+        "verified": None,
+        "en": None,
+        "chs": None,
+        "cht": None,
+        "jp": None,
+        "synonym": None,
+        "kana": None
+    }
+    for i in range(0, len(g)):
+        if g[i].text == "Main Title":
+            t_dic["main"] = re.sub("\(a\d+\)", "", v[i].text).strip("\n\t")
+        elif g[i].text == "Official Title":
+            if re.search("verified", str(v[i])):
+                t_dic["verified"] = v[i].find("label").text
+            if re.search("language: english", str(v[i])):
+                t_dic["en"] = v[i].find("label").text
+            elif re.search("span>zh-Hant", str(v[i])):
+                t_dic["cht"] = v[i].find("label").text
+            elif re.search("span>zh-Hans", str(v[i])):
+                t_dic["chs"] = v[i].find("label").text
+            elif re.search("language: japanese", str(v[i])):
+                t_dic["jp"] = v[i].find("label").text
+        elif g[i].text == "Synonym":
+            t_dic["synonym"] = v[i].text
+        elif g[i].text == "Kana":
+            t_dic["kana"] = v[i].text
+    return t_dic
+
+if __name__ == "__main__":
+    print("start")
+    # 年份，季度
+    id_list = (get_list(2022, 1))
+    for i in id_list:
+        url = f"http://api.anidb.net:9001/httpapi?request=anime&client=autobangumi&clientver=1&protover=1&aid={i}"
+        req = requests.get(url)
+        soup = BeautifulSoup(req.text, "xml")
+        titles = soup.find("titles")["official"]
+        for item in titles:
+            print(item)