[common] add '_extract_nextdata' method

gallery_dl/extractor/common.py

@@ -591,6 +591,10 @@ class Extractor():
         return util.json_loads(text.extr(
             page, '<script type="application/ld+json">', "</script>"))
 
+    def _extract_nextdata(self, page):
+        return util.json_loads(text.extr(
+            page, ' id="__NEXT_DATA__" type="application/json">', "</script>"))
+
     def _prepare_ddosguard_cookies(self):
         if not self.cookies.get("__ddg2", domain=self.cookies_domain):
             self.cookies.set(

gallery_dl/extractor/mangapark.py

@@ -43,8 +43,7 @@ class MangaparkChapterExtractor(MangaparkBase, ChapterExtractor):
         ChapterExtractor.__init__(self, match, url)
 
     def metadata(self, page):
-        data = util.json_loads(text.extr(
+        data = self._extract_nextdata(page)
-            page, 'id="__NEXT_DATA__" type="application/json">', '<'))
         chapter = (data["props"]["pageProps"]["dehydratedState"]
                    ["queries"][0]["state"]["data"]["data"])
         manga = chapter["comicNode"]["data"]

gallery_dl/extractor/patreon.py

@@ -286,15 +286,12 @@ class PatreonExtractor(Extractor):
         return [genmap[ft] for ft in filetypes]
 
     def _extract_bootstrap(self, page):
-        data = text.extr(
+        try:
-            page, 'id="__NEXT_DATA__" type="application/json">', '</script')
+            data = self._extract_nextdata(page)
-        if data:
+            env = data["props"]["pageProps"]["bootstrapEnvelope"]
-            try:
+            return env.get("pageBootstrap") or env["bootstrap"]
-                data = util.json_loads(data)
+        except Exception as exc:
-                env = data["props"]["pageProps"]["bootstrapEnvelope"]
+            self.log.debug("%s: %s", exc.__class__.__name__, exc)
-                return env.get("pageBootstrap") or env["bootstrap"]
-            except Exception as exc:
-                self.log.debug("%s: %s", exc.__class__.__name__, exc)
 
         bootstrap = text.extr(
             page, 'window.patreon = {"bootstrap":', '},"apiServer"')

gallery_dl/extractor/slideshare.py

@@ -10,7 +10,7 @@
 """Extractors for https://www.slideshare.net/"""
 
 from .common import GalleryExtractor
-from .. import text, util
+from .. import text
 
 
 class SlidesharePresentationExtractor(GalleryExtractor):
@@ -31,8 +31,7 @@ class SlidesharePresentationExtractor(GalleryExtractor):
         GalleryExtractor.__init__(self, match, url)
 
     def metadata(self, page):
-        data = util.json_loads(text.extr(
+        data = self._extract_nextdata(page)
-            page, 'id="__NEXT_DATA__" type="application/json">', '</script>'))
         self.slideshow = slideshow = data["props"]["pageProps"]["slideshow"]
 
         return {