def testGetEbookUrls(self):
searchRequest = SearchRequest(query="novel")
urls = self.n1.get_ebook_urls(searchRequest)
self.assertEqual(1, len(urls))
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&cat=7020,8010&limit=100&t=search&extended=1&offset=0&q=novel",
urls[0],
)
self.args = SearchRequest(author="anauthor", title="atitle", category=getCategoryByAnyInput(7020))
queries = self.n1.get_ebook_urls(self.args)
self.assertEqual(1, len(urls))
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&cat=7020&extended=1&limit=100&offset=0&q=anauthor+atitle&t=search",
queries[0],
)
self.newznab1.searchTypes = ["book"]
self.n1 = NewzNab(self.newznab1)
self.args = SearchRequest(author="anauthor", title="atitle", category=getCategoryByAnyInput(7020))
queries = self.n1.get_ebook_urls(self.args)
self.assertEqual(1, len(urls))
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&author=anauthor&cat=7020&extended=1&limit=100&offset=0&t=book&title=atitle",
queries[0],
)
def testUrlGeneration(self):
self.args = SearchRequest(query="aquery")
urls = self.omgwtf.get_search_urls(self.args)
self.assertEqual(1, len(urls))
self.assertEqual("https://api.omgwtfnzbs.org/xml/?api=apikey&user=anuser&search=aquery", urls[0])
self.args = SearchRequest(query="aquery", category=getCategoryByAnyInput("tvhd"))
urls = self.omgwtf.get_search_urls(self.args)
self.assertEqual(1, len(urls))
self.assertEqual("https://api.omgwtfnzbs.org/xml/?api=apikey&user=anuser&search=aquery&catid=20", urls[0])
self.args = SearchRequest(query="aquery", maxage=100)
urls = self.omgwtf.get_search_urls(self.args)
self.assertEqual(1, len(urls))
self.assertEqual("https://api.omgwtfnzbs.org/xml/?api=apikey&user=anuser&search=aquery&retention=100", urls[0])
self.args = SearchRequest(query="aquery", category=getCategoryByAnyInput("tvhd"), maxage=100)
urls = self.omgwtf.get_search_urls(self.args)
self.assertEqual(1, len(urls))
self.assertEqual("https://api.omgwtfnzbs.org/xml/?api=apikey&user=anuser&search=aquery&retention=100&catid=20", urls[0])
self.args = SearchRequest()
urls = self.omgwtf.get_search_urls(self.args)
self.assertEqual(1, len(urls))
self.assertEqual("https://rss.omgwtfnzbs.org/rss-download.php?api=apikey&user=anuser", urls[0])
self.args = SearchRequest(category=getCategoryByAnyInput("tvhd"))
urls = self.omgwtf.get_search_urls(self.args)
self.assertEqual(1, len(urls))
self.assertEqual("https://rss.omgwtfnzbs.org/rss-download.php?api=apikey&user=anuser&catid=20", urls[0])
def testUrlGeneration(self):
self.args = SearchRequest(query="aquery")
urls = self.omgwtf.get_search_urls(self.args)
self.assertEqual(1, len(urls))
self.assertEqual("https://api.omgwtfnzbs.org/xml/?api=apikey&user=anuser&search=aquery", urls[0])
self.args = SearchRequest(query="aquery", category=getCategoryByAnyInput("tvhd"))
urls = self.omgwtf.get_search_urls(self.args)
self.assertEqual(1, len(urls))
self.assertEqual("https://api.omgwtfnzbs.org/xml/?api=apikey&user=anuser&search=aquery&catid=20", urls[0])
self.args = SearchRequest(query="aquery", maxage=100)
urls = self.omgwtf.get_search_urls(self.args)
self.assertEqual(1, len(urls))
self.assertEqual("https://api.omgwtfnzbs.org/xml/?api=apikey&user=anuser&search=aquery&retention=100", urls[0])
self.args = SearchRequest(query="aquery", category=getCategoryByAnyInput("tvhd"), maxage=100)
urls = self.omgwtf.get_search_urls(self.args)
self.assertEqual(1, len(urls))
self.assertEqual("https://api.omgwtfnzbs.org/xml/?api=apikey&user=anuser&search=aquery&retention=100&catid=20", urls[0])
self.args = SearchRequest()
urls = self.omgwtf.get_search_urls(self.args)
self.assertEqual(1, len(urls))
self.assertEqual("https://rss.omgwtfnzbs.org/rss-download.php?api=apikey&user=anuser", urls[0])
self.args = SearchRequest(category=getCategoryByAnyInput("tvhd"))
urls = self.omgwtf.get_search_urls(self.args)
self.assertEqual(1, len(urls))
self.assertEqual("https://rss.omgwtfnzbs.org/rss-download.php?api=apikey&user=anuser&catid=20", urls[0])
def testGetEbookUrls(self):
searchRequest = SearchRequest(query="novel")
urls = self.n1.get_ebook_urls(searchRequest)
self.assertEqual(1, len(urls))
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&cat=7020,8010&limit=100&t=search&extended=1&offset=0&q=novel",
urls[0])
self.args = SearchRequest(author="anauthor",
title="atitle",
category=getCategoryByAnyInput(7020))
queries = self.n1.get_ebook_urls(self.args)
self.assertEqual(1, len(urls))
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&cat=7020&extended=1&limit=100&offset=0&q=anauthor+atitle&t=search",
queries[0])
self.newznab1.searchTypes = ["book"]
self.n1 = NewzNab(self.newznab1)
self.args = SearchRequest(author="anauthor",
title="atitle",
category=getCategoryByAnyInput(7020))
queries = self.n1.get_ebook_urls(self.args)
self.assertEqual(1, len(urls))
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&author=anauthor&cat=7020&extended=1&limit=100&offset=0&t=book&title=atitle",
queries[0])
def testGetShowSearchUrls(self):
self.args = SearchRequest(query="aquery")
urls = self.omgwtf.get_showsearch_urls(self.args)
self.assertEqual(1, len(urls))
self.assertEqual("https://api.omgwtfnzbs.org/xml/?api=apikey&user=anuser&search=aquery&catid=19,20,21", urls[0])
self.args = SearchRequest(query="aquery", category=getCategoryByAnyInput("tvhd"))
urls = self.omgwtf.get_showsearch_urls(self.args)
self.assertEqual(1, len(urls))
self.assertEqual("https://api.omgwtfnzbs.org/xml/?api=apikey&user=anuser&search=aquery&catid=20", urls[0])
self.args = SearchRequest(query="aquery", season=1)
urls = self.omgwtf.get_showsearch_urls(self.args)
self.assertEqual(1, len(urls))
self.assertEqual("https://api.omgwtfnzbs.org/xml/?api=apikey&user=anuser&search=aquery+s01&catid=19,20,21", urls[0])
self.args = SearchRequest(query="aquery", season=1, episode=2)
urls = self.omgwtf.get_showsearch_urls(self.args)
self.assertEqual(1, len(urls))
self.assertEqual("https://api.omgwtfnzbs.org/xml/?api=apikey&user=anuser&search=aquery+s01e02&catid=19,20,21", urls[0])
self.args = SearchRequest()
urls = self.omgwtf.get_showsearch_urls(self.args)
self.assertEqual(1, len(urls))
self.assertEqual("https://rss.omgwtfnzbs.org/rss-download.php?api=apikey&user=anuser&catid=19,20,21", urls[0])
self.args = SearchRequest(query="a showtitle", season="2016", episode="08/08")
urls = self.omgwtf.get_showsearch_urls(self.args)
self.assertEqual(1, len(urls))
self.assertEqual('a showtitle "2016 08 08"', furl(urls[0]).args["search"])
def testGetShowSearchUrls(self):
self.args = SearchRequest(query="aquery")
urls = self.omgwtf.get_showsearch_urls(self.args)
self.assertEqual(1, len(urls))
self.assertEqual("https://api.omgwtfnzbs.org/xml/?api=apikey&user=anuser&search=aquery&catid=19,20,21", urls[0])
self.args = SearchRequest(query="aquery", category=getCategoryByAnyInput("tvhd"))
urls = self.omgwtf.get_showsearch_urls(self.args)
self.assertEqual(1, len(urls))
self.assertEqual("https://api.omgwtfnzbs.org/xml/?api=apikey&user=anuser&search=aquery&catid=20", urls[0])
self.args = SearchRequest(query="aquery", season=1)
urls = self.omgwtf.get_showsearch_urls(self.args)
self.assertEqual(1, len(urls))
self.assertEqual("https://api.omgwtfnzbs.org/xml/?api=apikey&user=anuser&search=aquery+s01&catid=19,20,21", urls[0])
self.args = SearchRequest(query="aquery", season=1, episode=2)
urls = self.omgwtf.get_showsearch_urls(self.args)
self.assertEqual(1, len(urls))
self.assertEqual("https://api.omgwtfnzbs.org/xml/?api=apikey&user=anuser&search=aquery+s01e02&catid=19,20,21", urls[0])
self.args = SearchRequest()
urls = self.omgwtf.get_showsearch_urls(self.args)
self.assertEqual(1, len(urls))
self.assertEqual("https://rss.omgwtfnzbs.org/rss-download.php?api=apikey&user=anuser&catid=19,20,21", urls[0])
def get_comic_urls(self, search_request):
if not search_request.category:
search_request.category = getCategoryByAnyInput("comic")
if hasattr(self.settings, "comicCategory") and self.settings.comicCategory:
self.debug("Using %s as determined newznab comic category" % self.settings.comicCategory)
search_request.category.category.newznabCategories = [self.settings.comicCategory]
return self.get_search_urls(search_request)
def get_showsearch_urls(self, search_request):
if search_request.category is None:
search_request.category = getCategoryByAnyInput("tv")
url = self.build_base_url("tvsearch", search_request.category, offset=search_request.offset)
if search_request.identifier_key:
canBeConverted, toType, id = infos.convertIdToAny(search_request.identifier_key, self.search_ids, search_request.identifier_value)
if canBeConverted:
search_request.identifier_key = toType.replace("tvrage", "rid").replace("tvdb", "tvdbid")
search_request.identifier_value = id
else:
self.info("Unable to search using ID type %s" % search_request.identifier_key)
return []
url.add({search_request.identifier_key: search_request.identifier_value})
if search_request.episode:
url.add({"ep": search_request.episode})
if search_request.season:
url.add({"season": search_request.season})
if search_request.query:
url.add({"q": search_request.query})
if search_request.maxage:
url.add({"maxage": search_request.maxage})
return [url.url]
def get_anime_urls(self, search_request):
if not search_request.category:
search_request.category = getCategoryByAnyInput("anime")
if hasattr(self.settings, "animeCategory") and self.settings.animeCategory:
self.debug("Using %s as determinted newznab anime category" % self.settings.animeCategory)
search_request.category.category.newznabCategories = [self.settings.animeCategory]
return self.get_search_urls(search_request)
def get_moviesearch_urls(self, search_request):
if search_request.category is None:
search_request.category = getCategoryByAnyInput("movies")
# A lot of indexers seem to disregard the "q" parameter for "movie" search, so if we have a query use regular search instead
if search_request.query:
url = self.build_base_url("search",
search_request.category,
offset=search_request.offset)
url.add({"q": search_request.query})
else:
url = self.build_base_url("movie",
search_request.category,
offset=search_request.offset)
if search_request.identifier_key:
canBeConverted, toType, id = infos.convertIdToAny(
search_request.identifier_key, self.search_ids,
search_request.identifier_value)
if canBeConverted:
search_request.identifier_key = toType.replace(
"tvrage",
"rid").replace("tvdb",
"tvdbid").replace("imdb", "imdbid")
search_request.identifier_value = id
else:
self.info("Unable to search using ID type %s" %
search_request.identifier_key)
return []
url.add({
search_request.identifier_key:
search_request.identifier_value
})
return [url.url]
def get_showsearch_urls(self, search_request):
if search_request.category is None:
search_request.category = getCategoryByAnyInput("tv")
url = self.build_base_url("tvsearch",
search_request.category,
offset=search_request.offset)
if search_request.identifier_key:
canBeConverted, toType, id = infos.convertIdToAny(
search_request.identifier_key, self.search_ids,
search_request.identifier_value)
if canBeConverted:
search_request.identifier_key = toType.replace(
"tvrage", "rid").replace("tvdb", "tvdbid")
search_request.identifier_value = id
else:
self.info("Unable to search using ID type %s" %
search_request.identifier_key)
return []
url.add({
search_request.identifier_key:
search_request.identifier_value
})
if search_request.episode:
url.add({"ep": search_request.episode})
if search_request.season:
url.add({"season": search_request.season})
if search_request.query:
url.add({"q": search_request.query.replace(":", "")})
if search_request.maxage:
url.add({"maxage": search_request.maxage})
return [url.url]
def get_ebook_urls(self, search_request):
if not search_request.category:
search_request.category = getCategoryByAnyInput("ebook")
if hasattr(self.settings,
"ebookCategory") and self.settings.ebookCategory:
self.debug("Using %s as determined newznab ebook category" %
self.settings.ebookCategory)
search_request.category.category.newznabCategories = [
self.settings.ebookCategory
]
if search_request.author or search_request.title:
if "book" in self.searchTypes:
# API search
url = self.build_base_url("book",
search_request.category,
offset=search_request.offset)
if search_request.author:
url.add({"author": search_request.author})
if search_request.title:
url.add({"title": search_request.title.replace(":", "")})
return [url.url]
else:
search_request.query = "%s %s" % (
search_request.author if search_request.author else "",
search_request.title.replace(":", "")
if search_request.title else "")
return self.get_search_urls(search_request)
else:
# internal search
return self.get_search_urls(search_request)
def testGetCategoryByAnyInput(self):
config.settings = Bunch.fromDict(config.initialConfig)
cats = "2000"
result = categories.getCategoryByAnyInput(cats)
self.assertEqual("newznab", result.type)
self.assertEqual([2000], result.original)
self.assertEqual("movies", result.category.name)
cats = u"2000"
result = categories.getCategoryByAnyInput(cats)
self.assertEqual("newznab", result.type)
self.assertEqual([2000], result.original)
self.assertEqual("movies", result.category.name)
cats = ""
result = categories.getCategoryByAnyInput(cats)
self.assertEqual("hydra", result.type)
self.assertEqual("all", result.category.name)
cats = []
result = categories.getCategoryByAnyInput(cats)
self.assertEqual("newznab", result.type)
self.assertEqual("all", result.category.name)
cats = None
result = categories.getCategoryByAnyInput(cats)
self.assertEqual("hydra", result.type)
self.assertEqual("all", result.category.name)
cats = 2000
result = categories.getCategoryByAnyInput(cats)
self.assertEqual("newznab", result.type)
self.assertEqual([2000], result.original)
self.assertEqual("movies", result.category.name)
cats = [2000, 2010]
result = categories.getCategoryByAnyInput(cats)
self.assertEqual("newznab", result.type)
self.assertEqual([2000, 2010], result.original)
self.assertEqual("movies", result.category.name)
cats = ["2000", "2010"]
result = categories.getCategoryByAnyInput(cats)
self.assertEqual("newznab", result.type)
self.assertEqual([2000, 2010], result.original)
self.assertEqual("movies", result.category.name)
cats = "movies"
result = categories.getCategoryByAnyInput(cats)
self.assertEqual("hydra", result.type)
self.assertEqual("movies", result.category.name)
def get_moviesearch_urls(self, search_request):
if search_request.category is None:
search_request.category = getCategoryByAnyInput("movies")
if search_request.identifier_key:
canBeConverted, toType, id = infos.convertIdToAny(search_request.identifier_key, ["imdb"], search_request.identifier_value)
if canBeConverted:
search_request.query = "tt%s" % id
return self.get_search_urls(search_request)
def get_moviesearch_urls(self, search_request):
if search_request.category is None:
search_request.category = getCategoryByAnyInput("movies")
if search_request.identifier_key:
canBeConverted, toType, id = infos.convertIdToAny(search_request.identifier_key, ["imdb"], search_request.identifier_value)
if canBeConverted:
search_request.query = "tt%s" % id
return self.get_search_urls(search_request)
def get_anime_urls(self, search_request):
if not search_request.category:
search_request.category = getCategoryByAnyInput("anime")
if hasattr(self.settings,
"animeCategory") and self.settings.animeCategory:
self.debug("Using %s as determined newznab anime category" %
self.settings.animeCategory)
search_request.category.category.newznabCategories = [
self.settings.animeCategory
]
return self.get_search_urls(search_request)
def get_comic_urls(self, search_request):
if not search_request.category:
search_request.category = getCategoryByAnyInput("comic")
if hasattr(self.settings,
"comicCategory") and self.settings.comicCategory:
self.debug("Using %s as determinted newznab comic category" %
self.settings.comicCategory)
search_request.category.category.newznabCategories = [
self.settings.comicCategory
]
return self.get_search_urls(search_request)
def get_showsearch_urls(self, search_request):
if search_request.category is None:
search_request.category = getCategoryByAnyInput("tv")
#Should get most results, apparently there is no way of using "or" searches
if search_request.query:
query = search_request.query
elif search_request.title:
query = search_request.title
else:
query = ""
if search_request.season:
if search_request.episode:
search_request.query = "{0} s{1:02d}e{2:02d}".format(query, int(search_request.season), int(search_request.episode))
else:
search_request.query = "{0} s{1:02d}".format(query, int(search_request.season))
return self.get_search_urls(search_request)
def get_ebook_urls(self, search_request):
if not search_request.category:
search_request.category = getCategoryByAnyInput("ebook")
if search_request.author or search_request.title:
if "book" in self.searchTypes:
#API search
url = self.build_base_url("book", search_request.category, offset=search_request.offset)
if search_request.author:
url.add({"author": search_request.author})
if search_request.title:
url.add({"title": search_request.title})
return [url.url]
else:
search_request.query = "%s %s" % (search_request.author if search_request.author else "", search_request.title if search_request.title else "")
return self.get_search_urls(search_request)
else:
#internal search
return self.get_search_urls(search_request)
def get_ebook_urls(self, search_request):
if not search_request.category:
search_request.category = getCategoryByAnyInput("ebook")
if hasattr(self.settings, "ebookCategory") and self.settings.ebookCategory:
self.debug("Using %s as determinted newznab ebook category" % self.settings.ebookCategory)
search_request.category.category.newznabCategories = [self.settings.ebookCategory]
if search_request.author or search_request.title:
if "book" in self.searchTypes:
# API search
url = self.build_base_url("book", search_request.category, offset=search_request.offset)
if search_request.author:
url.add({"author": search_request.author})
if search_request.title:
url.add({"title": search_request.title})
return [url.url]
else:
search_request.query = "%s %s" % (search_request.author if search_request.author else "", search_request.title if search_request.title else "")
return self.get_search_urls(search_request)
else:
# internal search
return self.get_search_urls(search_request)
def get_showsearch_urls(self, search_request):
if search_request.category is None:
search_request.category = getCategoryByAnyInput("tv")
#Should get most results, apparently there is no way of using "or" searches
if search_request.query:
query = search_request.query
elif search_request.title:
query = search_request.title
else:
query = ""
if search_request.season:
if search_request.episode:
if self.isNumber(search_request.episode):
search_request.query = "{0} s{1:02d}e{2:02d}".format(query, int(search_request.season), int(search_request.episode))
else:
search_request.query = '%s "%s %s"' % (search_request.query, search_request.season, search_request.episode.replace("/", " "))
self.debug("Assuming we're searching for a daily show. Using query: " + search_request.query)
elif self.isNumber(search_request.season):
search_request.query = "{0} s{1:02d}".format(query, int(search_request.season))
return self.get_search_urls(search_request)
def get_moviesearch_urls(self, search_request):
if search_request.category is None:
search_request.category = getCategoryByAnyInput("movies")
#A lot of indexers seem to disregard the "q" parameter for "movie" search, so if we have a query use regular search instead
if search_request.query:
url = self.build_base_url("search", search_request.category, offset=search_request.offset)
url.add({"q": search_request.query})
else:
url = self.build_base_url("movie", search_request.category, offset=search_request.offset)
if search_request.identifier_key:
canBeConverted, toType, id = infos.convertIdToAny(search_request.identifier_key, self.search_ids, search_request.identifier_value)
if canBeConverted:
search_request.identifier_key = toType.replace("tvrage", "rid").replace("tvdb", "tvdbid").replace("imdb", "imdbid")
search_request.identifier_value = id
else:
self.info("Unable to search using ID type %s" % search_request.identifier_key)
return []
url.add({search_request.identifier_key: search_request.identifier_value})
return [url.url]
def testProcessSearchResults(self):
with open("mock/omgwtf_search.xml", encoding="latin-1") as f:
body = f.read()
result = self.omgwtf.process_query_result(body, SearchRequest())
entries = result.entries
self.assertEqual(3, len(entries))
self.assertEqual('atvshow.S02E09.720p.HDTV.DD5.1.x264-NTb', entries[0].title)
self.assertEqual("https://api.omgwtfnzbs.org/nzb/?id=x30FI&user=auser&api=apikey", entries[0].link)
self.assertEqual(2396942366, entries[0].size)
self.assertEqual("x30FI", entries[0].indexerguid)
self.assertEqual(1449855118, entries[0].epoch)
self.assertEqual("2015-12-11T17:31:58+00:00", entries[0].pubdate_utc)
self.assertEqual(18, entries[0].age_days)
self.assertTrue(entries[0].age_precise)
self.assertEqual(NzbSearchResult.HAS_NFO_NO, entries[0].has_nfo)
self.assertEqual("alt.binaries.hdtv", entries[0].group)
self.assertEqual(getCategoryByAnyInput("tvhd").category.name, entries[0].category.name)
self.assertEqual("https://omgwtfnzbs.org/details?id=x30FI", entries[0].details_link)
self.assertFalse(result.has_more)
self.assertTrue(result.total_known)
self.assertEqual(3, result.total)
self.assertEqual(NzbSearchResult.HAS_NFO_YES, entries[2].has_nfo)
def testProcessSearchResults(self):
with open("mock/omgwtf_search.xml", encoding="latin-1") as f:
body = f.read()
result = self.omgwtf.process_query_result(body, SearchRequest())
entries = result.entries
self.assertEqual(3, len(entries))
self.assertEqual('atvshow.S02E09.720p.HDTV.DD5.1.x264-NTb', entries[0].title)
self.assertEqual("https://api.omgwtfnzbs.org/nzb/?id=x30FI&user=auser&api=apikey", entries[0].link)
self.assertEqual(2396942366, entries[0].size)
self.assertEqual("x30FI", entries[0].indexerguid)
self.assertEqual(1449855118, entries[0].epoch)
self.assertEqual("2015-12-11T17:31:58+00:00", entries[0].pubdate_utc)
self.assertEqual(18, entries[0].age_days)
self.assertTrue(entries[0].age_precise)
self.assertEqual(NzbSearchResult.HAS_NFO_NO, entries[0].has_nfo)
self.assertEqual("alt.binaries.hdtv", entries[0].group)
self.assertEqual(getCategoryByAnyInput("tvhd").category.name, entries[0].category.name)
self.assertEqual("https://omgwtfnzbs.org/details?id=x30FI", entries[0].details_link)
self.assertFalse(result.has_more)
self.assertTrue(result.total_known)
self.assertEqual(3, result.total)
self.assertEqual(NzbSearchResult.HAS_NFO_YES, entries[2].has_nfo)
def testGetMovieSearchUrls(self):
self.args = SearchRequest(identifier_key="imdb", identifier_value="0169547")
urls = self.omgwtf.get_moviesearch_urls(self.args)
self.assertEqual(1, len(urls))
self.assertEqual("https://api.omgwtfnzbs.org/xml/?api=apikey&user=anuser&search=tt0169547&catid=15,16,17,18", urls[0])
self.args = SearchRequest(identifier_key="tmdb", identifier_value="14", category=getCategoryByAnyInput("movieshd"))
urls = self.omgwtf.get_moviesearch_urls(self.args)
self.assertEqual(1, len(urls))
self.assertEqual("https://api.omgwtfnzbs.org/xml/?api=apikey&user=anuser&search=tt0169547&catid=16", urls[0])
def get_comic_urls(self, search_request):
if not search_request.category:
search_request.category = getCategoryByAnyInput("comic")
return self.get_search_urls(search_request)
def testNewznabSearchQueries(self):
self.args = SearchRequest(query="aquery")
queries = self.n1.get_search_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&extended=1&limit=100&offset=0&q=aquery&t=search",
query)
self.args = SearchRequest(query=None)
queries = self.n1.get_search_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&extended=1&limit=100&offset=0&t=search",
query)
self.args = SearchRequest(query="")
queries = self.n1.get_search_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&extended=1&limit=100&offset=0&t=search",
query)
self.args = SearchRequest(category=getCategoryByAnyInput("audio"))
queries = self.n1.get_search_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&cat=3000&extended=1&limit=100&offset=0&t=search",
query)
self.args = SearchRequest()
queries = self.n1.get_showsearch_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&cat=5000&extended=1&limit=100&offset=0&t=tvsearch",
query)
self.args = SearchRequest(query=None)
queries = self.n1.get_showsearch_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&cat=5000&extended=1&limit=100&offset=0&t=tvsearch",
query)
self.args = SearchRequest(query="")
queries = self.n1.get_showsearch_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&cat=5000&extended=1&limit=100&offset=0&t=tvsearch",
query)
self.args = SearchRequest(category=getCategoryByAnyInput("all"))
queries = self.n1.get_showsearch_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&extended=1&limit=100&offset=0&t=tvsearch",
query)
self.args = SearchRequest(identifier_value="8511",
identifier_key="rid")
queries = self.n1.get_showsearch_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&cat=5000&extended=1&limit=100&offset=0&rid=8511&t=tvsearch",
query)
self.args = SearchRequest(identifier_value="8511",
identifier_key="rid",
season=1)
queries = self.n1.get_showsearch_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&cat=5000&extended=1&limit=100&offset=0&rid=8511&season=1&t=tvsearch",
query)
self.args = SearchRequest(identifier_value="8511",
identifier_key="rid",
season=1,
episode=2)
queries = self.n1.get_showsearch_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&cat=5000&ep=2&extended=1&limit=100&offset=0&rid=8511&season=1&t=tvsearch",
query)
self.args = SearchRequest(identifier_value="12345678",
identifier_key="imdbid")
queries = self.n1.get_moviesearch_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&cat=2000&extended=1&imdbid=12345678&limit=100&offset=0&t=movie",
query)
self.args = SearchRequest(identifier_value="12345678",
identifier_key="imdbid",
category=getCategoryByAnyInput("movieshd"))
queries = self.n1.get_moviesearch_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&cat=2040,2050,2060&extended=1&imdbid=12345678&limit=100&offset=0&t=movie",
query)
self.args = SearchRequest(category=getCategoryByAnyInput("movies"))
queries = self.n1.get_moviesearch_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&cat=2000&extended=1&limit=100&offset=0&t=movie",
query)
self.args = SearchRequest(category=getCategoryByAnyInput("movies"),
query=None)
queries = self.n1.get_moviesearch_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&cat=2000&extended=1&limit=100&offset=0&t=movie",
query)
self.args = SearchRequest(category=getCategoryByAnyInput("movies"),
query="")
queries = self.n1.get_moviesearch_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&cat=2000&extended=1&limit=100&offset=0&t=movie",
query)
config.settings.searching.forbiddenWords = "ignorethis"
self.args = SearchRequest(query="aquery",
forbiddenWords=["ignorethis"])
queries = self.n1.get_search_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&extended=1&limit=100&offset=0&q=aquery !ignorethis&t=search",
query)
config.settings.searching.forbiddenWords = "ignorethis"
self.args = SearchRequest(query="aquery",
forbiddenWords=["ignorethis"])
queries = self.n1.get_search_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&extended=1&limit=100&offset=0&q=aquery !ignorethis&t=search",
query)
def search(search_request):
if search_request.maxage is None and config.settings.searching.maxAge:
search_request.maxage = config.settings.searching.maxAge
logger.info("Will ignore results older than %d days" % search_request.maxage)
# Clean up cache
for k in list(pseudo_cache.keys()):
if pseudo_cache[k]["last_access"].replace(minutes=+5) < arrow.utcnow():
pseudo_cache.pop(k)
# Clean up old search results. We do this here because we don't have any background jobs and this is the function most regularly called
keepFor = config.settings.main.keepSearchResultsForDays
oldSearchResultsCount = SearchResult.select().where(SearchResult.firstFound < (datetime.date.today() - datetime.timedelta(days=keepFor))).count()
if oldSearchResultsCount > 0:
logger.info("Deleting %d search results from database that are older than %d days" % (oldSearchResultsCount, keepFor))
SearchResult.delete().where(SearchResult.firstFound < (datetime.date.today() - datetime.timedelta(days=keepFor))).execute()
else:
if logger.getEffectiveLevel() == logging.DEBUG:
logger.debug("%d search results stored in database" % SearchResult.select().count())
limit = search_request.limit
external_offset = int(search_request.offset)
search_hash = search_request.search_hash
categoryResult = categories.getCategoryByAnyInput(search_request.category)
search_request.category = categoryResult
if search_hash not in pseudo_cache.keys() or search_request.offset == 0: # If it's a new search (which starts with offset 0) do it again instead of using the cached results
logger.debug("Didn't find this query in cache or want to do a new search")
cache_entry = {"results": [], "indexer_infos": {}, "total": 0, "last_access": arrow.utcnow(), "offset": 0}
category = categoryResult.category
indexers_to_call = pick_indexers(search_request)
for p in indexers_to_call:
cache_entry["indexer_infos"][p] = {"has_more": True, "search_request": search_request, "total_included": False}
dbsearch = Search(internal=search_request.internal, query=search_request.query, category=categoryResult.category.pretty, identifier_key=search_request.identifier_key, identifier_value=search_request.identifier_value, season=search_request.season, episode=search_request.episode, type=search_request.type,
username=search_request.username)
# dbsearch.save()
cache_entry["dbsearch"] = dbsearch
# Find ignored words and parse query for ignored words
search_request.forbiddenWords = []
search_request.requiredWords = []
applyRestrictionsGlobal = config.settings.searching.applyRestrictions == "both" or (config.settings.searching.applyRestrictions == "internal" and search_request.internal) or (config.settings.searching.applyRestrictions == "external" and not search_request.internal)
applyRestrictionsCategory = category.applyRestrictions == "both" or (category.applyRestrictions == "internal" and search_request.internal) or (search_request.category.category.applyRestrictions == "external" and not search_request.internal)
if config.settings.searching.forbiddenWords and applyRestrictionsGlobal:
logger.debug("Using configured global forbidden words: %s" % config.settings.searching.forbiddenWords)
search_request.forbiddenWords.extend([x.lower().strip() for x in list(filter(bool, config.settings.searching.forbiddenWords.split(",")))])
if config.settings.searching.requiredWords and applyRestrictionsGlobal:
logger.debug("Using configured global required words: %s" % config.settings.searching.requiredWords)
search_request.requiredWords.extend([x.lower().strip() for x in list(filter(bool, config.settings.searching.requiredWords.split(",")))])
if category.forbiddenWords and applyRestrictionsCategory:
logger.debug("Using configured forbidden words for category %s: %s" % (category.pretty, category.forbiddenWords))
search_request.forbiddenWords.extend([x.lower().strip() for x in list(filter(bool, category.forbiddenWords.split(",")))])
if category.requiredWords and applyRestrictionsCategory:
logger.debug("Using configured required words for category %s: %s" % (category.pretty, category.requiredWords))
search_request.requiredWords.extend([x.lower().strip() for x in list(filter(bool, category.requiredWords.split(",")))])
if search_request.query:
forbiddenWords = [str(x[1]) for x in re.findall(r"[\s|\b](\-\-|!)(?P<term>\w+)", search_request.query)]
if len(forbiddenWords) > 0:
logger.debug("Query before removing NOT terms: %s" % search_request.query)
search_request.query = re.sub(r"[\s|\b](\-\-|!)(?P<term>\w+)", "", search_request.query)
logger.debug("Query after removing NOT terms: %s" % search_request.query)
logger.debug("Found NOT terms: %s" % ",".join(forbiddenWords))
search_request.forbiddenWords.extend(forbiddenWords)
pseudo_cache[search_hash] = cache_entry
else:
cache_entry = pseudo_cache[search_hash]
indexers_to_call = [indexer for indexer, info in cache_entry["indexer_infos"].items() if info["has_more"]]
dbsearch = cache_entry["dbsearch"]
logger.debug("Found search in cache")
logger.debug("Will search at indexers as long as we don't have enough results for the current offset+limit and any indexer has more results.")
while len(cache_entry["results"]) < external_offset + limit and len(indexers_to_call) > 0:
logger.debug("We want %d results but have only %d so far" % ((external_offset + limit), len(cache_entry["results"])))
logger.debug("%d indexers still have results" % len(indexers_to_call))
search_request.offset = cache_entry["offset"]
logger.debug("Searching indexers with offset %d" % search_request.offset)
result = search_and_handle_db(dbsearch, {x: search_request for x in indexers_to_call})
logger.debug("All search calls to indexers completed")
search_results = []
indexers_to_call = []
for indexer, queries_execution_result in result["results"].items():
#Drastically improves db access time but means that if one database write fails all fail. That's a risk we need to take
with db.atomic():
logger.debug("%s returned %d results. Writing them to database..." % (indexer, len(queries_execution_result.results)))
for result in queries_execution_result.results:
if result.title is None or result.link is None or result.indexerguid is None:
logger.info("Skipping result with missing data: %s" % result)
continue
searchResult, _ = SearchResult().create_or_get(indexer=indexer.indexer, guid=result.indexerguid, title= result.title, link= result.link, details= result.details_link)
result.searchResultId = searchResult.id
search_results.append(result)
logger.debug("Written results results to database")
cache_entry["indexer_infos"][indexer].update(
{"did_search": queries_execution_result.didsearch, "indexer": indexer.name, "search_request": search_request, "has_more": queries_execution_result.has_more, "total": queries_execution_result.total, "total_known": queries_execution_result.total_known,
"indexer_search": queries_execution_result.indexerSearchEntry})
if queries_execution_result.has_more:
indexers_to_call.append(indexer)
logger.debug("%s still has more results so we could use it the next round" % indexer)
if queries_execution_result.total_known:
if not cache_entry["indexer_infos"][indexer]["total_included"]:
cache_entry["total"] += queries_execution_result.total
logger.debug("%s reports %d total results. We'll include in the total this time only" % (indexer, queries_execution_result.total))
cache_entry["indexer_infos"][indexer]["total_included"] = True
elif queries_execution_result.has_more:
logger.debug("%s doesn't report an exact number of results so let's just add another 100 to the total" % indexer)
cache_entry["total"] += 100
if search_request.internal or config.settings.searching.removeDuplicatesExternal:
logger.debug("Searching for duplicates")
countBefore = len(search_results)
grouped_by_sameness = find_duplicates(search_results)
allresults = []
for group in grouped_by_sameness:
if search_request.internal:
for i in group:
# We give each group of results a unique value by which they can be identified later
i.hash = hash(group[0].details_link)
allresults.append(i)
else:
# We sort by age first and then by indexerscore so the newest result with the highest indexer score is chosen
group = sorted(group, key=lambda x: x.epoch, reverse=True)
group = sorted(group, key=lambda x: x.indexerscore, reverse=True)
allresults.append(group[0])
search_results = allresults
if not search_request.internal:
countAfter = len(search_results)
countRemoved = countBefore - countAfter
logger.info("Removed %d duplicates from %d results" % (countRemoved, countBefore))
search_results = sorted(search_results, key=lambda x: x.epoch, reverse=True)
cache_entry["results"].extend(search_results)
cache_entry["offset"] += limit
if search_request.internal:
logger.debug("We have %d cached results and return them all because we search internally" % len(cache_entry["results"]))
nzb_search_results = copy.deepcopy(cache_entry["results"][external_offset:])
else:
logger.debug("We have %d cached results and return %d-%d of %d total available accounting for the limit set for the API search" % (len(cache_entry["results"]), external_offset, external_offset + limit, cache_entry["total"]))
nzb_search_results = copy.deepcopy(cache_entry["results"][external_offset:(external_offset + limit)])
cache_entry["last_access"] = arrow.utcnow()
logger.info("Returning %d results" % len(nzb_search_results))
return {"results": nzb_search_results, "indexer_infos": cache_entry["indexer_infos"], "dbsearchid": cache_entry["dbsearch"].id, "total": cache_entry["total"], "offset": external_offset}
def search(search_request):
logger.info("Starting new search: %s" % search_request)
if search_request.maxage is None and config.settings.searching.maxAge:
search_request.maxage = config.settings.searching.maxAge
logger.info("Will ignore results older than %d days" % search_request.maxage)
# Clean up cache
for k in list(pseudo_cache.keys()):
if pseudo_cache[k]["last_access"].replace(minutes=+5) < arrow.utcnow():
pseudo_cache.pop(k)
# Clean up old search results. We do this here because we don't have any background jobs and this is the function most regularly called
keepFor = config.settings.main.keepSearchResultsForDays
oldSearchResultsCount = countOldSearchResults(keepFor)
if oldSearchResultsCount > 0:
logger.info("Deleting %d search results from database that are older than %d days" % (oldSearchResultsCount, keepFor))
SearchResult.delete().where(SearchResult.firstFound < (datetime.date.today() - datetime.timedelta(days=keepFor))).execute()
else:
if logger.getEffectiveLevel() == logging.DEBUG:
logger.debug("%d search results stored in database" % SearchResult.select().count())
limit = search_request.limit
external_offset = int(search_request.offset)
search_hash = search_request.search_hash
categoryResult = categories.getCategoryByAnyInput(search_request.category)
search_request.category = categoryResult
if search_hash not in pseudo_cache.keys() or search_request.offset == 0: # If it's a new search (which starts with offset 0) do it again instead of using the cached results
logger.debug("Didn't find this query in cache or want to do a new search")
cache_entry = {"results": [], "indexer_infos": {}, "total": 0, "last_access": arrow.utcnow(), "offset": 0, "rejected": SearchModule.getRejectedCountDict()}
category = categoryResult.category
indexers_to_call = pick_indexers(search_request)
for p in indexers_to_call:
cache_entry["indexer_infos"][p] = {"has_more": True, "search_request": search_request, "total_included": False}
dbsearch = Search(internal=search_request.internal, query=search_request.query, category=categoryResult.category.pretty, identifier_key=search_request.identifier_key, identifier_value=search_request.identifier_value, season=search_request.season, episode=search_request.episode,
type=search_request.type, title=search_request.title, author=search_request.author, username=search_request.username)
saveSearch(dbsearch)
# dbsearch.save()
cache_entry["dbsearch"] = dbsearch
# Find ignored words and parse query for ignored words
search_request.forbiddenWords = []
search_request.requiredWords = []
applyRestrictionsGlobal = config.settings.searching.applyRestrictions == "both" or (config.settings.searching.applyRestrictions == "internal" and search_request.internal) or (config.settings.searching.applyRestrictions == "external" and not search_request.internal)
applyRestrictionsCategory = category.applyRestrictions == "both" or (category.applyRestrictions == "internal" and search_request.internal) or (search_request.category.category.applyRestrictions == "external" and not search_request.internal)
if config.settings.searching.forbiddenWords and applyRestrictionsGlobal:
logger.debug("Using configured global forbidden words: %s" % config.settings.searching.forbiddenWords)
search_request.forbiddenWords.extend([x.lower().strip() for x in list(filter(bool, config.settings.searching.forbiddenWords.split(",")))])
if config.settings.searching.requiredWords and applyRestrictionsGlobal:
logger.debug("Using configured global required words: %s" % config.settings.searching.requiredWords)
search_request.requiredWords.extend([x.lower().strip() for x in list(filter(bool, config.settings.searching.requiredWords.split(",")))])
if category.forbiddenWords and applyRestrictionsCategory:
logger.debug("Using configured forbidden words for category %s: %s" % (category.pretty, category.forbiddenWords))
search_request.forbiddenWords.extend([x.lower().strip() for x in list(filter(bool, category.forbiddenWords.split(",")))])
if category.requiredWords and applyRestrictionsCategory:
logger.debug("Using configured required words for category %s: %s" % (category.pretty, category.requiredWords))
search_request.requiredWords.extend([x.lower().strip() for x in list(filter(bool, category.requiredWords.split(",")))])
if search_request.query:
forbiddenWords = [str(x[1]) for x in re.findall(r"[\s|\b](\-\-|!)(?P<term>\w+)", search_request.query)]
if len(forbiddenWords) > 0:
logger.debug("Query before removing NOT terms: %s" % search_request.query)
search_request.query = re.sub(r"[\s|\b](\-\-|!)(?P<term>\w+)", "", search_request.query)
logger.debug("Query after removing NOT terms: %s" % search_request.query)
logger.debug("Found NOT terms: %s" % ",".join(forbiddenWords))
search_request.forbiddenWords.extend(forbiddenWords)
cache_entry["forbiddenWords"] = search_request.forbiddenWords
cache_entry["requiredWords"] = search_request.requiredWords
cache_entry["query"] = search_request.query
pseudo_cache[search_hash] = cache_entry
else:
cache_entry = pseudo_cache[search_hash]
indexers_to_call = [indexer for indexer, info in cache_entry["indexer_infos"].items() if info["has_more"]]
dbsearch = cache_entry["dbsearch"]
search_request.forbiddenWords = cache_entry["forbiddenWords"]
search_request.requiredWords = cache_entry["requiredWords"]
search_request.query = cache_entry["query"]
logger.debug("Found search in cache")
logger.debug("Will search at indexers as long as we don't have enough results for the current offset+limit and any indexer has more results.")
if search_request.loadAll:
logger.debug("Requested to load all results. Will continue to search until all indexers are exhausted")
while (len(cache_entry["results"]) < external_offset + limit or search_request.loadAll) and len(indexers_to_call) > 0:
if len(cache_entry["results"]) < external_offset + limit:
logger.debug("We want %d results but have only %d so far" % ((external_offset + limit), len(cache_entry["results"])))
elif search_request.loadAll:
logger.debug("All results requested. Continuing to search.")
logger.debug("%d indexers still have results" % len(indexers_to_call))
search_request.offset = cache_entry["offset"]
logger.debug("Searching indexers with offset %d" % search_request.offset)
result = search_and_handle_db(dbsearch, {x: search_request for x in indexers_to_call})
logger.debug("All search calls to indexers completed")
search_results = []
indexers_to_call = []
waslocked = False
before = arrow.now()
if databaseLock.locked():
logger.debug("Database accesses locked by other search. Will wait for our turn.")
waslocked = True
databaseLock.acquire()
if waslocked:
after = arrow.now()
took = (after - before).seconds * 1000 + (after - before).microseconds / 1000
logger.debug("Waited %dms for database lock" % took)
for indexer, queries_execution_result in result["results"].items():
with db.atomic():
logger.info("%s returned %d results" % (indexer, len(queries_execution_result.results)))
for result in queries_execution_result.results:
if result.title is None or result.link is None or result.indexerguid is None:
logger.info("Skipping result with missing data: %s" % result)
continue
try:
searchResultId = hashlib.sha1(str(indexer.indexer.id) + result.indexerguid).hexdigest()
tryGetOrCreateSearchResultDbEntry(searchResultId, indexer.indexer.id, result)
result.searchResultId = searchResultId
search_results.append(result)
except (IntegrityError, OperationalError) as e:
logger.error("Error while trying to save search result to database. Skipping it. Error: %s" % e)
cache_entry["indexer_infos"][indexer].update(
{"did_search": queries_execution_result.didsearch, "indexer": indexer.name, "search_request": search_request, "has_more": queries_execution_result.has_more, "total": queries_execution_result.total, "total_known": queries_execution_result.total_known,
"indexer_search": queries_execution_result.indexerSearchEntry, "rejected": queries_execution_result.rejected, "processed_results": queries_execution_result.loaded_results})
if queries_execution_result.has_more:
indexers_to_call.append(indexer)
logger.debug("%s still has more results so we could use it the next round" % indexer)
if queries_execution_result.total_known:
if not cache_entry["indexer_infos"][indexer]["total_included"]:
cache_entry["total"] += queries_execution_result.total
logger.debug("%s reports %d total results. We'll include in the total this time only" % (indexer, queries_execution_result.total))
cache_entry["indexer_infos"][indexer]["total_included"] = True
elif queries_execution_result.has_more:
logger.debug("%s doesn't report an exact number of results so let's just add another 100 to the total" % indexer)
cache_entry["total"] += 100
for rejectKey in cache_entry["rejected"].keys():
if rejectKey in cache_entry["indexer_infos"][indexer]["rejected"].keys():
cache_entry["rejected"][rejectKey] += cache_entry["indexer_infos"][indexer]["rejected"][rejectKey]
databaseLock.release()
logger.debug("Searching for duplicates")
numberResultsBeforeDuplicateRemoval = len(search_results)
grouped_by_sameness, uniqueResultsPerIndexer = find_duplicates(search_results)
allresults = []
for group in grouped_by_sameness:
if search_request.internal:
for i in group:
# We give each group of results a unique value by which they can be identified later
i.hash = hash(group[0].details_link)
allresults.append(i)
else:
# We sort by age first and then by indexerscore so the newest result with the highest indexer score is chosen
group = sorted(group, key=lambda x: x.epoch, reverse=True)
group = sorted(group, key=lambda x: x.indexerscore, reverse=True)
allresults.append(group[0])
search_results = allresults
with databaseLock:
for indexer, infos in cache_entry["indexer_infos"].iteritems():
if indexer.name in uniqueResultsPerIndexer.keys(): # If the search failed it isn't contained in the duplicates list
uniqueResultsCount = uniqueResultsPerIndexer[infos["indexer"]]
processedResults = infos["processed_results"]
logger.debug("Indexer %s had a unique results share of %d%% (%d of %d total results were only provided by this indexer)" % (indexer.name, 100 / (numberResultsBeforeDuplicateRemoval / uniqueResultsCount), uniqueResultsCount, numberResultsBeforeDuplicateRemoval))
infos["indexer_search"].uniqueResults = uniqueResultsCount
infos["indexer_search"].processedResults = processedResults
infos["indexer_search"].save()
if not search_request.internal:
countAfter = len(search_results)
countRemoved = numberResultsBeforeDuplicateRemoval - countAfter
logger.info("Removed %d duplicates from %d results" % (countRemoved, numberResultsBeforeDuplicateRemoval))
search_results = sorted(search_results, key=lambda x: x.epoch, reverse=True)
cache_entry["results"].extend(search_results)
cache_entry["offset"] += limit
if len(indexers_to_call) == 0:
logger.info("All indexers exhausted")
elif len(cache_entry["results"]) >= external_offset + limit:
logger.debug("Loaded a total of %d results which is enough for the %d requested. Stopping search." % (len(cache_entry["results"]), (external_offset + limit)))
if search_request.internal:
logger.debug("We have %d cached results and return them all because we search internally" % len(cache_entry["results"]))
nzb_search_results = copy.deepcopy(cache_entry["results"][external_offset:])
else:
logger.debug("We have %d cached results and return %d-%d of %d total available accounting for the limit set for the API search" % (len(cache_entry["results"]), external_offset, external_offset + limit, cache_entry["total"]))
nzb_search_results = copy.deepcopy(cache_entry["results"][external_offset:(external_offset + limit)])
cache_entry["last_access"] = arrow.utcnow()
for k, v in cache_entry["rejected"].items():
if v > 0:
logger.info("Rejected %d because: %s" % (v, k))
logger.info("Returning %d results" % len(nzb_search_results))
return {"results": nzb_search_results, "indexer_infos": cache_entry["indexer_infos"], "dbsearchid": cache_entry["dbsearch"].id, "total": cache_entry["total"], "offset": external_offset, "rejected": cache_entry["rejected"].items()}
def get_ebook_urls(self, search_request):
if not search_request.query and (search_request.author or search_request.title):
search_request.query = "%s %s" % (search_request.author if search_request.author else "", search_request.title if search_request.title else "")
if search_request.category is None:
search_request.category = getCategoryByAnyInput("ebook")
return self.get_search_urls(search_request)
def get_audiobook_urls(self, search_request):
if search_request.category is None:
search_request.category = getCategoryByAnyInput("audiobook")
return self.get_search_urls(search_request)
def search(search_request):
# type: (bool, nzbhydra.search.SearchRequest) -> Dict[unicode, future.types.newint.newint]
if search_request.maxage is None and config.settings.searching.maxAge:
search_request.maxage = config.settings.searching.maxAge
logger.info("Will ignore results older than %d days" % search_request.maxage)
# Clean up cache
for k in list(pseudo_cache.keys()):
if pseudo_cache[k]["last_access"].replace(minutes=+5) < arrow.utcnow():
pseudo_cache.pop(k)
# Clean up old search results. We do this here because we don't have any background jobs and this is the function most regularly called
keepFor = config.settings.main.keepSearchResultsForDays
oldSearchResultsCount = SearchResult.select().where(SearchResult.firstFound < (datetime.date.today() - datetime.timedelta(days=keepFor))).count()
if oldSearchResultsCount > 0:
logger.info("Deleting %d search results from database that are older than %d days" % (oldSearchResultsCount, keepFor))
SearchResult.delete().where(SearchResult.firstFound < (datetime.date.today() - datetime.timedelta(days=keepFor))).execute()
limit = search_request.limit
external_offset = int(search_request.offset)
search_hash = search_request.search_hash
if search_hash not in pseudo_cache.keys() or search_request.offset == 0: # If it's a new search (which starts with offset 0) do it again instead of using the cached results
logger.debug("Didn't find this query in cache or want to do a new search")
cache_entry = {"results": [], "indexer_infos": {}, "total": 0, "last_access": arrow.utcnow(), "offset": 0}
indexers_to_call = pick_indexers(search_request)
for p in indexers_to_call:
cache_entry["indexer_infos"][p] = {"has_more": True, "search_request": search_request, "total_included": False}
categoryResult = categories.getCategoryByAnyInput(search_request.category)
search_request.category = categoryResult
category = categoryResult.category
dbsearch = Search(internal=search_request.internal, query=search_request.query, category=categoryResult.category.pretty, identifier_key=search_request.identifier_key, identifier_value=search_request.identifier_value, season=search_request.season, episode=search_request.episode, type=search_request.type,
username=search_request.username)
# dbsearch.save()
cache_entry["dbsearch"] = dbsearch
# Find ignored words and pParse query for ignored words
search_request.forbiddenWords = []
search_request.requiredWords = []
if config.settings.searching.forbiddenWords:
logger.debug("Using configured global forbidden words: %s" % config.settings.searching.forbiddenWords)
search_request.forbiddenWords.extend([x.lower().strip() for x in list(filter(bool, config.settings.searching.forbiddenWords.split(",")))])
if config.settings.searching.requiredWords:
logger.debug("Using configured global required words: %s" % config.settings.searching.requiredWords)
search_request.requiredWords.extend([x.lower().strip() for x in list(filter(bool, config.settings.searching.requiredWords.split(",")))])
if category.applyRestrictions == "both" or (category.applyRestrictions == "internal" and search_request.internal) or (category.applyRestrictions == "external" and not search_request.internal):
if category.forbiddenWords:
logger.debug("Using configured forbidden words for category %s: %s" % (category.pretty, category.forbiddenWords))
search_request.forbiddenWords.extend([x.lower().strip() for x in list(filter(bool, category.forbiddenWords.split(",")))])
if category.requiredWords:
logger.debug("Using configured required words for category %s: %s" % (category.pretty, category.requiredWords))
search_request.requiredWords.extend([x.lower().strip() for x in list(filter(bool, category.requiredWords.split(",")))])
if search_request.query:
forbiddenWords = [str(x[1]) for x in re.findall(r"[\s|\b](\-\-|!)(?P<term>\w+)", search_request.query)]
if len(forbiddenWords) > 0:
logger.debug("Query before removing NOT terms: %s" % search_request.query)
search_request.query = re.sub(r"[\s|\b](\-\-|!)(?P<term>\w+)", "", search_request.query)
logger.debug("Query after removing NOT terms: %s" % search_request.query)
logger.debug("Found NOT terms: %s" % ",".join(forbiddenWords))
search_request.forbiddenWords.extend(forbiddenWords)
pseudo_cache[search_hash] = cache_entry
else:
cache_entry = pseudo_cache[search_hash]
indexers_to_call = [indexer for indexer, info in cache_entry["indexer_infos"].items() if info["has_more"]]
dbsearch = cache_entry["dbsearch"]
logger.debug("Found search in cache")
logger.debug("Will search at indexers as long as we don't have enough results for the current offset+limit and any indexer has more results.")
while len(cache_entry["results"]) < external_offset + limit and len(indexers_to_call) > 0:
logger.debug("We want %d results but have only %d so far" % ((external_offset + limit), len(cache_entry["results"])))
logger.debug("%d indexers still have results" % len(indexers_to_call))
search_request.offset = cache_entry["offset"]
logger.debug("Searching indexers with offset %d" % search_request.offset)
result = search_and_handle_db(dbsearch, {x: search_request for x in indexers_to_call})
search_results = []
indexers_to_call = []
for indexer, queries_execution_result in result["results"].items():
with db.atomic():
for result in queries_execution_result.results:
if result.title is None or result.link is None or result.indexerguid is None:
logger.info("Skipping result with missing data: %s" % result)
continue
searchResult = SearchResult().get_or_create(indexer=indexer.indexer, title=result.title, link=result.link, details=result.details_link, guid=result.indexerguid)
searchResult = searchResult[0] # Second is a boolean determining if the search result was created
result.searchResultId = searchResult.id
search_results.append(result)
logger.debug("%s returned %d results" % (indexer, len(queries_execution_result.results)))
cache_entry["indexer_infos"][indexer].update(
{"did_search": queries_execution_result.didsearch, "indexer": indexer.name, "search_request": search_request, "has_more": queries_execution_result.has_more, "total": queries_execution_result.total, "total_known": queries_execution_result.total_known,
"indexer_search": queries_execution_result.indexerSearchEntry})
if queries_execution_result.has_more:
indexers_to_call.append(indexer)
logger.debug("%s still has more results so we could use it the next round" % indexer)
if queries_execution_result.total_known:
if not cache_entry["indexer_infos"][indexer]["total_included"]:
cache_entry["total"] += queries_execution_result.total
logger.debug("%s reports %d total results. We'll include in the total this time only" % (indexer, queries_execution_result.total))
cache_entry["indexer_infos"][indexer]["total_included"] = True
elif queries_execution_result.has_more:
logger.debug("%s doesn't report an exact number of results so let's just add another 100 to the total" % indexer)
cache_entry["total"] += 100
if search_request.internal or config.settings.searching.removeDuplicatesExternal:
countBefore = len(search_results)
grouped_by_sameness = find_duplicates(search_results)
allresults = []
for group in grouped_by_sameness:
if search_request.internal:
for i in group:
# We give each group of results a unique value by which they can be identified later
i.hash = hash(group[0].guid)
allresults.append(i)
else:
# We sort by age first and then by indexerscore so the newest result with the highest indexer score is chosen
group = sorted(group, key=lambda x: x.epoch, reverse=True)
group = sorted(group, key=lambda x: x.indexerscore, reverse=True)
allresults.append(group[0])
search_results = allresults
if not search_request.internal:
countAfter = len(search_results)
countRemoved = countBefore - countAfter
logger.info("Removed %d duplicates from %d results" % (countRemoved, countBefore))
search_results = sorted(search_results, key=lambda x: x.epoch, reverse=True)
cache_entry["results"].extend(search_results)
cache_entry["offset"] += limit
if search_request.internal:
logger.debug("We have %d cached results and return them all because we search internally" % len(cache_entry["results"]))
nzb_search_results = copy.deepcopy(cache_entry["results"][external_offset:])
else:
logger.debug("We have %d cached results and return %d-%d of %d total available accounting for the limit set for the API search" % (len(cache_entry["results"]), external_offset, external_offset + limit, cache_entry["total"]))
nzb_search_results = copy.deepcopy(cache_entry["results"][external_offset:(external_offset + limit)])
cache_entry["last_access"] = arrow.utcnow()
return {"results": nzb_search_results, "indexer_infos": cache_entry["indexer_infos"], "dbsearchid": cache_entry["dbsearch"].id, "total": cache_entry["total"], "offset": external_offset}
def get_comic_urls(self, search_request):
if not search_request.category:
search_request.category = getCategoryByAnyInput("comic")
logger.info("Searching for comics in ebook category")
return self.get_search_urls(search_request)
def testNewznabSearchQueries(self):
self.args = SearchRequest(query="aquery")
queries = self.n1.get_search_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&extended=1&limit=100&offset=0&q=aquery&t=search", query
)
self.args = SearchRequest(query=None)
queries = self.n1.get_search_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&extended=1&limit=100&offset=0&t=search", query
)
self.args = SearchRequest(query="")
queries = self.n1.get_search_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&extended=1&limit=100&offset=0&t=search", query
)
self.args = SearchRequest(category=getCategoryByAnyInput("audio"))
queries = self.n1.get_search_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&cat=3000&extended=1&limit=100&offset=0&t=search", query
)
self.args = SearchRequest()
queries = self.n1.get_showsearch_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&cat=5000&extended=1&limit=100&offset=0&t=tvsearch", query
)
self.args = SearchRequest(query=None)
queries = self.n1.get_showsearch_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&cat=5000&extended=1&limit=100&offset=0&t=tvsearch", query
)
self.args = SearchRequest(query="")
queries = self.n1.get_showsearch_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&cat=5000&extended=1&limit=100&offset=0&t=tvsearch", query
)
self.args = SearchRequest(category=getCategoryByAnyInput("all"))
queries = self.n1.get_showsearch_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&extended=1&limit=100&offset=0&t=tvsearch", query
)
self.args = SearchRequest(identifier_value="8511", identifier_key="rid")
queries = self.n1.get_showsearch_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&cat=5000&extended=1&limit=100&offset=0&rid=8511&t=tvsearch",
query,
)
self.args = SearchRequest(identifier_value="8511", identifier_key="rid", season=1)
queries = self.n1.get_showsearch_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&cat=5000&extended=1&limit=100&offset=0&rid=8511&season=1&t=tvsearch",
query,
)
self.args = SearchRequest(identifier_value="8511", identifier_key="rid", season=1, episode=2)
queries = self.n1.get_showsearch_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&cat=5000&ep=2&extended=1&limit=100&offset=0&rid=8511&season=1&t=tvsearch",
query,
)
self.args = SearchRequest(identifier_value="12345678", identifier_key="imdbid")
queries = self.n1.get_moviesearch_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&cat=2000&extended=1&imdbid=12345678&limit=100&offset=0&t=movie",
query,
)
self.args = SearchRequest(
identifier_value="12345678", identifier_key="imdbid", category=getCategoryByAnyInput("movieshd")
)
queries = self.n1.get_moviesearch_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&cat=2040,2050,2060&extended=1&imdbid=12345678&limit=100&offset=0&t=movie",
query,
)
self.args = SearchRequest(category=getCategoryByAnyInput("movies"))
queries = self.n1.get_moviesearch_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&cat=2000&extended=1&limit=100&offset=0&t=movie", query
)
self.args = SearchRequest(category=getCategoryByAnyInput("movies"), query=None)
queries = self.n1.get_moviesearch_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&cat=2000&extended=1&limit=100&offset=0&t=movie", query
)
self.args = SearchRequest(category=getCategoryByAnyInput("movies"), query="")
queries = self.n1.get_moviesearch_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&cat=2000&extended=1&limit=100&offset=0&t=movie", query
)
config.settings.searching.forbiddenWords = "ignorethis"
self.args = SearchRequest(query="aquery", forbiddenWords=["ignorethis"])
queries = self.n1.get_search_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&extended=1&limit=100&offset=0&q=aquery !ignorethis&t=search",
query,
)
config.settings.searching.forbiddenWords = "ignorethis"
self.args = SearchRequest(query="aquery", forbiddenWords=["ignorethis"])
queries = self.n1.get_search_urls(self.args)
assert len(queries) == 1
query = queries[0]
self.assertUrlEqual(
"https://indexer.com/api?apikey=apikeyindexer.com&extended=1&limit=100&offset=0&q=aquery !ignorethis&t=search",
query,
)
def testGetMovieSearchUrls(self):
self.args = SearchRequest(identifier_key="imdb", identifier_value="0169547")
urls = self.omgwtf.get_moviesearch_urls(self.args)
self.assertEqual(1, len(urls))
self.assertEqual("https://api.omgwtfnzbs.org/xml/?api=apikey&user=anuser&search=tt0169547&catid=15,16,17,18", urls[0])
self.args = SearchRequest(identifier_key="tmdb", identifier_value="14", category=getCategoryByAnyInput("movieshd"))
urls = self.omgwtf.get_moviesearch_urls(self.args)
self.assertEqual(1, len(urls))
self.assertEqual("https://api.omgwtfnzbs.org/xml/?api=apikey&user=anuser&search=tt0169547&catid=16", urls[0])
def get_ebook_urls(self, search_request):
if not search_request.query and (search_request.author or search_request.title):
search_request.query = "%s %s" % (search_request.author if search_request.author else "", search_request.title if search_request.title else "")
if search_request.category is None:
search_request.category = getCategoryByAnyInput("ebook")
return self.get_search_urls(search_request)
def get_audiobook_urls(self, search_request):
if search_request.category is None:
search_request.category = getCategoryByAnyInput("audiobook")
return self.get_search_urls(search_request)
def get_comic_urls(self, search_request):
if not search_request.category:
search_request.category = getCategoryByAnyInput("comic")
logger.info("Searching for comics in ebook category")
return self.get_search_urls(search_request)
