first test at having a cli for dumping anime information from anidb in yaml formatHEADmaster

1 files changed, 48 insertions, 23 deletions

diff --git a/anidb/__init__.py b/anidb/__init__.py
index 29e9b78..c9eef78 100644
--- a/anidb/__init__.py
+++ b/anidb/__init__.py
@@ -1,7 +1,10 @@
+import os
+import time
+from datetime import datetime
+
 import requests
 from bs4 import BeautifulSoup
 
-from datetime import datetime
 
 BASE_URL = "http://api.anidb.net:9001/httpapi"
 SEARCH_URL = "http://anisearch.outrance.pl/"
@@ -20,6 +23,16 @@ class AniDB:
     self._cache = {}
 
   def _request(self, datapage, params={}, cache=True):
+
+    cache_filename = f'cache_{params["aid"]}.xml'
+
+    if os.path.exists(cache_filename):
+        print('D: cache_filename exists, return its content:', cache_filename)
+        with open(cache_filename, 'r', encoding='utf8') as fpi:
+            return fpi.read()
+
+    time.sleep(3) # avoid being banned with subsequent requests
+
     params.update({
       'client': self.client_id,
       'clientver': self.client_ver,
@@ -28,7 +41,14 @@ class AniDB:
     })
     r = requests.get(BASE_URL, params=params)
     r.raise_for_status()
-    return r
+
+    #print('D: r.text:', r.text)
+
+    print('D: creating cache file:', cache_filename)
+    with open(cache_filename, 'w', encoding='utf8') as fpo:
+        fpo.write(r.text)
+
+    return r.text
 
   # Anime http://wiki.anidb.net/w/HTTP_API_Definition#Access
 
@@ -45,22 +65,26 @@ class AniDB:
     results = []
     animetitles = BeautifulSoup(r.text, 'xml').animetitles
     for anime in animetitles.find_all('anime'):
-      results.append(Anime({
-        'id': int(anime['id']),
-        'title': str(anime.find('title', attrs={'type': "main"}).string)
-      }, partial=True, updater=lambda: self.get(anime['id'])))
+        print('D: got anime: ', anime)
+        aid = int(anime['aid'])
+        print('D: got aid: ', aid)
+        #results.append(Anime({
+        #    'aid': aid,
+        #    'title': str(anime.find('title', attrs={'type': "main"}).string)
+        #}, partial=True, updater=lambda: self.get(aid)))
+        results.append(self.get(aid))
+        print('D: result appended')
 
     return results
 
-  def get(self, id):
+  def get(self, aid):
     """
     Allows retrieval of non-file or episode related information for a specific anime by AID (AniDB anime id).
     http://wiki.anidb.net/w/HTTP_API_Definition#Anime
     """
-    id = int(id) # why?
-
-    r = self._request("anime", {'aid': id})
-    soup = BeautifulSoup(r.text, 'xml')
+    r = self._request("anime", {'aid': aid})
+    #print('D: got in AniDB.get(), r:', r)
+    soup = BeautifulSoup(r, 'xml')
     if soup.error is not None:
       raise Exception(soup.error.string)
 
@@ -68,25 +92,26 @@ class AniDB:
     titles = anime.titles
 
     a = Anime({
-      'id': id,
+      'aid': aid,
       'type': str(anime.type.string),
       'episodecount': int(anime.episodecount.string),
-      'startdate': datetime(*list(map(int, anime.startdate.string.split("-")))),
-      'enddate': datetime(*list(map(int, anime.enddate.string.split("-")))),
+      #'startdate': datetime(*list(map(int, anime.startdate.string.split("-")))),
+      #'enddate': datetime(*list(map(int, anime.enddate.string.split("-")))),
       'titles': [(
         str(title.string),
         title['type'] if 'type' in title else "unknown"
       ) for title in anime.find_all('title')],
       'title': str(titles.find('title', attrs={'type': "main"}).string),
       'relatedanime': [],
-      'url': str(anime.url.string),
+      'url': str(anime.url.string if anime.url else None),
       'creators': [],
-      'description': str(anime.description.string),
-      'ratings': SmartDict({
-        'permanent': float(anime.ratings.permanent.string),
-        'temporary': float(anime.ratings.temporary.string),
-        'review': float(anime.ratings.review.string)
-      }),
+      'description': str(anime.description.string if anime.description else ''),
+      #'ratings': SmartDict({
+      #  'permanent': float(anime.ratings.permanent.string),
+      #  'temporary': float(anime.ratings.temporary.string),
+      #  'review': float(anime.ratings.review.string if anime.ratings.review
+      #      else 0)
+      #}),
       'picture': "http://img7.anidb.net/pics/anime/" + str(anime.picture.string),
       'categories': [],
       'tags': [],
@@ -94,7 +119,7 @@ class AniDB:
       'episodes': [],
     })
 
-    self._cache[id] = a
+    self._cache[aid] = a
 
     return a
 
@@ -136,4 +161,4 @@ class Anime:
         raise AttributeError("no attribute called '%s'" % name)
 
   def __repr__(self):
-    return u'<Anime %i "%s">' % (self.id, self.title)
\ No newline at end of file
+    return u'<Anime %i "%s">' % (self.aid, self.title)