Merge remote-tracking branch 'lubimyczytac/add_lubimyczytac.pl_meta_p…

…rovider' into Develop

# Conflicts:
#	optional-requirements.txt

cps/metadata_provider/comicvine.py

@@ -17,49 +17,68 @@
 #  along with this program. If not, see <http://www.gnu.org/licenses/>.
 
 # ComicVine api document: https://comicvine.gamespot.com/api/documentation
+from typing import Dict, List, Optional
+from urllib.parse import quote
 
 import requests
-from cps.services.Metadata import Metadata
+from cps.services.Metadata import MetaRecord, MetaSourceInfo, Metadata
 
 
 class ComicVine(Metadata):
     __name__ = "ComicVine"
     __id__ = "comicvine"
+    DESCRIPTION = "ComicVine Books"
+    META_URL = "https://comicvine.gamespot.com/"
+    API_KEY = "57558043c53943d5d1e96a9ad425b0eb85532ee6"
+    BASE_URL = (
+        f"https://comicvine.gamespot.com/api/search?api_key={API_KEY}"
+        f"&resources=issue&query="
+    )
+    QUERY_PARAMS = "&sort=name:desc&format=json"
+    HEADERS = {"User-Agent": "Not Evil Browser"}
 
-    def search(self, query, generic_cover=""):
+    def search(
+        self, query: str, generic_cover: str = "", locale: str = "en"
+    ) -> Optional[List[MetaRecord]]:
         val = list()
-        apikey = "57558043c53943d5d1e96a9ad425b0eb85532ee6"
         if self.active:
-            headers = {
-                'User-Agent': 'Not Evil Browser'
-            }
-
-            result = requests.get("https://comicvine.gamespot.com/api/search?api_key="
-                                  + apikey + "&resources=issue&query=" + query + "&sort=name:desc&format=json", headers=headers)
-            for r in result.json().get('results'):
-                seriesTitle = r['volume'].get('name', "")
-                if r.get('store_date'):
-                    dateFomers = r.get('store_date')
-                else:
-                    dateFomers = r.get('date_added')
-                v = dict()
-                v['id'] = r['id']
-                v['title'] = seriesTitle + " #" + r.get('issue_number', "0") + " - " + ( r.get('name', "") or "")
-                v['authors'] = r.get('authors', [])
-                v['description'] = r.get('description', "")
-                v['publisher'] = ""
-                v['publishedDate'] = dateFomers
-                v['tags'] = ["Comics", seriesTitle]
-                v['rating'] = 0
-                v['series'] = seriesTitle
-                v['cover'] = r['image'].get('original_url')
-                v['source'] = {
-                    "id": self.__id__,
-                    "description": "ComicVine Books",
-                    "link": "https://comicvine.gamespot.com/"
-                }
-                v['url'] = r.get('site_detail_url', "")
-                val.append(v)
+            title_tokens = list(self.get_title_tokens(query, strip_joiners=False))
+            if title_tokens:
+                tokens = [quote(t.encode("utf-8")) for t in title_tokens]
+                query = "%20".join(tokens)
+            result = requests.get(
+                f"{ComicVine.BASE_URL}{query}{ComicVine.QUERY_PARAMS}",
+                headers=ComicVine.HEADERS,
+            )
+            for result in result.json()["results"]:
+                match = self._parse_search_result(
+                    result=result, generic_cover=generic_cover, locale=locale
+                )
+                val.append(match)
         return val
 
-
+    def _parse_search_result(
+        self, result: Dict, generic_cover: str, locale: str
+    ) -> MetaRecord:
+        series = result["volume"].get("name", "")
+        series_index = result.get("issue_number", 0)
+        issue_name = result.get("name", "")
+        match = MetaRecord(
+            id=result["id"],
+            title=f"{series}#{series_index} - {issue_name}",
+            authors=result.get("authors", []),
+            url=result.get("site_detail_url", ""),
+            source=MetaSourceInfo(
+                id=self.__id__,
+                description=ComicVine.DESCRIPTION,
+                link=ComicVine.META_URL,
+            ),
+            series=series,
+        )
+        match.cover = result["image"].get("original_url", generic_cover)
+        match.description = result.get("description", "")
+        match.publishedDate = result.get("store_date", result.get("date_added"))
+        match.series_index = series_index
+        match.tags = ["Comics", series]
+        match.identifiers = {"comicvine": match.id}
+        return match

cps/metadata_provider/google.py

@@ -17,39 +17,93 @@
 #  along with this program. If not, see <http://www.gnu.org/licenses/>.
 
 # Google Books api document: https://developers.google.com/books/docs/v1/using
-
+from typing import Dict, List, Optional
+from urllib.parse import quote
 
 import requests
-from cps.services.Metadata import Metadata
+
+from cps.isoLanguages import get_lang3, get_language_name
+from cps.services.Metadata import MetaRecord, MetaSourceInfo, Metadata
+
 
 class Google(Metadata):
     __name__ = "Google"
     __id__ = "google"
+    DESCRIPTION = "Google Books"
+    META_URL = "https://books.google.com/"
+    BOOK_URL = "https://books.google.com/books?id="
+    SEARCH_URL = "https://www.googleapis.com/books/v1/volumes?q="
+    ISBN_TYPE = "ISBN_13"
 
-    def search(self, query, generic_cover=""):
+    def search(
+        self, query: str, generic_cover: str = "", locale: str = "en"
+    ) -> Optional[List[MetaRecord]]:
+        val = list()    
         if self.active:
-            val = list()
-            result = requests.get("https://www.googleapis.com/books/v1/volumes?q="+query.replace(" ","+"))
-            for r in result.json().get('items'):
-                v = dict()
-                v['id'] = r['id']
-                v['title'] = r['volumeInfo'].get('title',"")
-                v['authors'] = r['volumeInfo'].get('authors', [])
-                v['description'] = r['volumeInfo'].get('description', "")
-                v['publisher'] = r['volumeInfo'].get('publisher', "")
-                v['publishedDate'] = r['volumeInfo'].get('publishedDate', "")
-                v['tags'] = r['volumeInfo'].get('categories', [])
-                v['rating'] = r['volumeInfo'].get('averageRating', 0)
-                if r['volumeInfo'].get('imageLinks'):
-                    v['cover'] = r['volumeInfo']['imageLinks']['thumbnail'].replace("http://", "https://")
-                else:
-                    v['cover'] = "/../../../static/generic_cover.jpg"
-                v['source'] = {
-                    "id": self.__id__,
-                    "description": "Google Books",
-                    "link": "https://books.google.com/"}
-                v['url'] = "https://books.google.com/books?id=" + r['id']
-                val.append(v)
-            return val
 
+            title_tokens = list(self.get_title_tokens(query, strip_joiners=False))
+            if title_tokens:
+                tokens = [quote(t.encode("utf-8")) for t in title_tokens]
+                query = "+".join(tokens)
+            results = requests.get(Google.SEARCH_URL + query)
+            for result in results.json()["items"]:
+                val.append(
+                    self._parse_search_result(
+                        result=result, generic_cover=generic_cover, locale=locale
+                    )
+                )
+        return val
+
+    def _parse_search_result(
+        self, result: Dict, generic_cover: str, locale: str
+    ) -> MetaRecord:
+        match = MetaRecord(
+            id=result["id"],
+            title=result["volumeInfo"]["title"],
+            authors=result["volumeInfo"].get("authors", []),
+            url=Google.BOOK_URL + result["id"],
+            source=MetaSourceInfo(
+                id=self.__id__,
+                description=Google.DESCRIPTION,
+                link=Google.META_URL,
+            ),
+        )
+
+        match.cover = self._parse_cover(result=result, generic_cover=generic_cover)
+        match.description = result["volumeInfo"].get("description", "")
+        match.languages = self._parse_languages(result=result, locale=locale)
+        match.publisher = result["volumeInfo"].get("publisher", "")
+        match.publishedDate = result["volumeInfo"].get("publishedDate", "")
+        match.rating = result["volumeInfo"].get("averageRating", 0)
+        match.series, match.series_index = "", 1
+        match.tags = result["volumeInfo"].get("categories", [])
+
+        match.identifiers = {"google": match.id}
+        match = self._parse_isbn(result=result, match=match)
+        return match
+
+    @staticmethod
+    def _parse_isbn(result: Dict, match: MetaRecord) -> MetaRecord:
+        identifiers = result["volumeInfo"].get("industryIdentifiers", [])
+        for identifier in identifiers:
+            if identifier.get("type") == Google.ISBN_TYPE:
+                match.identifiers["isbn"] = identifier.get("identifier")
+                break
+        return match
+
+    @staticmethod
+    def _parse_cover(result: Dict, generic_cover: str) -> str:
+        if result["volumeInfo"].get("imageLinks"):
+            cover_url = result["volumeInfo"]["imageLinks"]["thumbnail"]
+            return cover_url.replace("http://", "https://")
+        return generic_cover
 
+    @staticmethod
+    def _parse_languages(result: Dict, locale: str) -> List[str]:
+        language_iso2 = result["volumeInfo"].get("language", "")
+        languages = (
+            [get_language_name(locale, get_lang3(language_iso2))]
+            if language_iso2
+            else []
+        )
+        return languages