code cleanup to use nameext_from_url

gallery_dl/extractor/batoto.py

@@ -44,14 +44,11 @@ class BatotoExtractor(AsynchronousExtractor):
         page = self.request(self.url, params=params).text
         data = self.get_job_metadata(page)
         yield Message.Version, 1
-        yield Message.Directory, data
+        yield Message.Directory, data.copy()
         for i in range(int(data["count"])):
             next_url, image_url = self.get_page_urls(page)
-            filename = text.unquote(text.filename_from_url(image_url))
-            name, ext = os.path.splitext(filename)
+            text.nameext_from_url(image_url, data)
             data["page"] = i+1
-            data["name"] = name
-            data["extension"] = ext[1:]
             yield Message.Url, image_url, data.copy()
             if next_url:
                 params["p"] += 1

gallery_dl/extractor/booru.py

@@ -59,13 +59,7 @@ class BooruExtractor(Extractor):
     def get_file_metadata(self, data):
         """Collect metadata for a downloadable file"""
         data["category"] = self.info["category"]
-        data["filename"] = text.unquote(
-            text.filename_from_url(self.get_file_url(data))
-        )
-        name, ext = os.path.splitext(data["filename"])
-        data["name"] = name
-        data["extension"] = ext[1:]
-        return data
+        return text.nameext_from_url(self.get_file_url(data), data)
 
     def get_file_url(self, data):
         """Extract download-url from 'data'"""

gallery_dl/extractor/deviantart.py

@@ -85,17 +85,15 @@ class DeviantArtExtractor(AsynchronousExtractor):
                 url   , pos = text.extract(image, ' data-super-img="', '"', pos)
                 width , pos = text.extract(image, ' data-super-width="', '"', pos)
                 height, pos = text.extract(image, ' data-super-height="', '"', pos)
-        name, ext = os.path.splitext(text.filename_from_url(url))
-        return url, {
+        data = {
             "index": index,
             "title": match.group(1),
             "artist": match.group(2),
             "date": match.group(3),
             "width": width,
             "height": height,
-            "name": name,
-            "extension": ext[1:],
         }
+        return url, text.nameext_from_url(url, data)
 
     @staticmethod
     def extract_data(txt, attr, pattern):

gallery_dl/extractor/exhentai.py

@@ -58,10 +58,8 @@ class ExhentaiExtractor(Extractor):
             urlkey = "origurl"
         for num, image in enumerate(self.get_images(url), 1):
             image.update(data)
-            name, ext = os.path.splitext(text.filename_from_url(image["url"]))
             image["num"] = num
-            image["name"] = name
-            image["extension"] = ext[1:]
+            text.nameext_from_url(image["url"], image)
             if "/fullimg.php" in image[urlkey]:
                 time.sleep(random.uniform(1, 2))
             yield Message.Url, image[urlkey], image

gallery_dl/extractor/hbrowse.py

@@ -36,10 +36,8 @@ class HbrowseExtractor(Extractor):
         yield Message.Version, 1
         yield Message.Directory, data
         for num, url in enumerate(self.get_image_urls(page), 1):
-            name, ext = os.path.splitext(text.filename_from_url(url))
-            data["name"] = name
-            data["extension"] = ext[1:]
             data["num"] = num
+            text.nameext_from_url(url, data)
             yield Message.Url, url, data
 
     def get_job_metadata(self, page):

gallery_dl/extractor/hentaifoundry.py

@@ -70,14 +70,12 @@ class HentaiFoundryExtractor(Extractor):
         page = self.request(url).text
         index = text.extract(url, '/', '/', len(self.url_base) + len(self.artist))[0]
         title, pos = text.extract(page, 'Pictures</a> &raquo; <span>', '<')
-        url  , pos = text.extract(page, '//pictures.hentai-foundry.com', '"', pos)#
-        name, ext = os.path.splitext(text.filename_from_url(url))
-        return "http://pictures.hentai-foundry.com" + url, {
+        url  , pos = text.extract(page, '//pictures.hentai-foundry.com', '"', pos)
+        data = {
             "index": index,
             "title": text.unescape(title),
-            "name": name,
-            "extension": ext[1:],
         }
+        return "http://pictures.hentai-foundry.com" + url, text.nameext_from_url(url, data)
 
     def set_filters(self, token):
         """Set site-internal filters to show all images"""

gallery_dl/extractor/hitomi.py

@@ -37,11 +37,8 @@ class HitomiExtractor(Extractor):
         yield Message.Version, 1
         yield Message.Directory, data
         for num, url in enumerate(images, 1):
-            name, ext = os.path.splitext(text.filename_from_url(url))
             data["num"] = num
-            data["name"] = name
-            data["extension"] = ext[1:]
-            yield Message.Url, url, data
+            yield Message.Url, url, text.nameext_from_url(url, data)
 
     def get_job_metadata(self, page):
         """Collect metadata for extractor-job"""

gallery_dl/extractor/imagebam.py

@@ -37,11 +37,8 @@ class ImagebamExtractor(AsynchronousExtractor):
         yield Message.Directory, data
         for image_url, image_id in self.get_images(data["first-url"]):
             data["id"] = image_id
-            data["filename"] = text.unquote(text.filename_from_url(image_url))
-            name, ext = os.path.splitext(data["filename"])
             data["num"] += 1
-            data["name"] = name
-            data["extension"] = ext[1:]
+            text.nameext_from_url(image_url, data)
             yield Message.Url, image_url, data.copy()
 
     def get_job_metadata(self):

gallery_dl/extractor/imgth.py

@@ -35,12 +35,8 @@ class ImgthExtractor(Extractor):
         yield Message.Version, 1
         yield Message.Directory, data
         for num, url in enumerate(self.get_images(page), 1):
-            name, ext = os.path.splitext(text.filename_from_url(url))
             data["num"] = num
-            data["name"] = name
-            data["extension"] = ext[1:]
-            yield Message.Url, url, data
-
+            yield Message.Url, url, text.nameext_from_url(url, data)
     def get_images(self, page):
         pnum = 0
         while True:

gallery_dl/extractor/kissmanga.py

@@ -38,12 +38,8 @@ class KissmangaExtractor(Extractor):
         yield Message.Version, 1
         yield Message.Directory, data
         for num, url in enumerate(imgs, 1):
-            filename = text.unquote(text.filename_from_url(url))
-            name, ext = os.path.splitext(filename)
             data["page"] = num
-            data["name"] = name
-            data["extension"] = ext[1:]
-            yield Message.Url, url, data
+            yield Message.Url, url, text.nameext_from_url(url, data)
 
     @staticmethod
     def get_job_metadata(page):

gallery_dl/extractor/mangareader.py

@@ -91,12 +91,7 @@ class MangaReaderExtractor(AsynchronousExtractor):
             width , pos = extr(page, '<img id="img" width="', '"', pos)
             height, pos = extr(page, ' height="', '"', pos)
         image, pos = extr(page, ' src="', '"', pos)
-        filename = text.unquote(text.filename_from_url(image))
-        name, ext = os.path.splitext(filename)
-
-        return self.url_base + url, image, {
+        return self.url_base + url, image, text.nameext_from_url(image, {
             "width": width,
             "height": height,
-            "name": name,
-            "extension": ext[1:],
-        }
+        })

gallery_dl/extractor/mangashare.py

@@ -34,12 +34,10 @@ class MangaShareExtractor(AsynchronousExtractor):
         page = self.request(self.url_fmt.format(self.part, 1)).text
         data = self.get_job_metadata(page)
         yield Message.Version, 1
-        yield Message.Directory, data
+        yield Message.Directory, data.copy()
         for i, url in zip(range(int(data["count"])), (self.get_image_urls(page))):
-            name, ext = os.path.splitext(text.filename_from_url(url))
-            data["name"] = name
-            data["extension"] = ext[1:]
             data["page"] = i+1
+            text.nameext_from_url(url, data)
             yield Message.Url, url, data.copy()
 
     @staticmethod

gallery_dl/extractor/mangastream.py

@@ -40,11 +40,8 @@ class MangaStreamExtractor(AsynchronousExtractor):
             if next_url:
                 page = self.request(next_url).text
             next_url, image_url = self.get_page_metadata(page)
-            filename = text.unquote(text.filename_from_url(image_url))
-            name, ext = os.path.splitext(filename)
+            text.nameext_from_url(image_url, data)
             data["page"] = i+1
-            data["name"] = name
-            data["extension"] = ext[1:]
             yield Message.Url, image_url, data.copy()
 
     def get_job_metadata(self, page):

gallery_dl/extractor/nijie.py

@@ -67,10 +67,8 @@ class NijieExtractor(AsynchronousExtractor):
         page = self.request(self.popup_url + image_id).text
         matches = re.findall('<img src="([^"]+)"', page)
         for index, url in enumerate(matches):
-            yield "https:" + url, {
+            yield "https:" + url, text.nameext_from_url(url, {
                 "count": len(matches),
                 "index": index,
                 "image-id": image_id,
-                "name" : text.filename_from_url(url),
-                "extension": url[url.rfind(".")+1:],
-            }
+            })

gallery_dl/extractor/sankaku.py

@@ -76,14 +76,11 @@ class SankakuExtractor(AsynchronousExtractor):
         image_url, pos = text.extract(page, '<li>Original: <a href="', '"')
         width    , pos = text.extract(page, '>', 'x', pos)
         height   , pos = text.extract(page, '', ' ', pos)
-        filename = text.filename_from_url(image_url)
-        name, ext = os.path.splitext(filename)
-        return {
+        data = text.nameext_from_url(image_url, {
             "id": image_id,
             "file-url": "https:" + image_url,
             "width": width,
             "height": height,
-            "md5": name,
-            "name": name,
-            "extension": ext[1:],
-        }
+        })
+        data["md5"] = data["name"]
+        return data

gallery_dl/extractor/spectrumnexus.py

@@ -41,10 +41,8 @@ class SpectrumNexusExtractor(AsynchronousExtractor):
         count = int(data["count"])
         for i in range(1, count+1):
             url = self.get_image_url(page)
-            name, ext = os.path.splitext(text.filename_from_url(url))
+            text.nameext_from_url(url, data)
             data["page"] = i
-            data["name"] = name
-            data["extension"] = ext[1:]
             yield Message.Url, url, data.copy()
             if i < count:
                 params["page"] += 1