New upstream version 1.28.0.upstream/1.28.0

1 files changed, 66 insertions, 57 deletions

diff --git a/gallery_dl/extractor/pixiv.py b/gallery_dl/extractor/pixiv.py
index 8c6e6d8..8ad061d 100644
--- a/gallery_dl/extractor/pixiv.py
+++ b/gallery_dl/extractor/pixiv.py
@@ -26,13 +26,14 @@ class PixivExtractor(Extractor):
     directory_fmt = ("{category}", "{user[id]} {user[account]}")
     filename_fmt = "{id}_p{num}.{extension}"
     archive_fmt = "{id}{suffix}.{extension}"
-    cookies_domain = None
+    cookies_domain = ".pixiv.net"
     sanity_url = "https://s.pximg.net/common/images/limit_sanity_level_360.png"
     mypixiv_url = "https://s.pximg.net/common/images/limit_mypixiv_360.png"
 
     def _init(self):
         self.api = PixivAppAPI(self)
         self.load_ugoira = self.config("ugoira", True)
+        self.load_ugoira_original = (self.load_ugoira == "original")
         self.max_posts = self.config("max-posts", 0)
         self.sanity_workaround = self.config("sanity", True)
         self.meta_user = self.config("metadata")
@@ -105,34 +106,7 @@ class PixivExtractor(Extractor):
         del work["image_urls"]
         del work["meta_pages"]
 
-        if work["type"] == "ugoira":
-            if self.load_ugoira:
-                try:
-                    return self._extract_ugoira(work)
-                except Exception as exc:
-                    self.log.warning(
-                        "%s: Unable to retrieve Ugoira metatdata (%s - %s)",
-                        work["id"], exc.__class__.__name__, exc)
-
-        elif work["page_count"] == 1:
-            url = meta_single_page["original_image_url"]
-            if url == self.sanity_url:
-                if self.sanity_workaround:
-                    self.log.warning("%s: 'sanity_level' warning", work["id"])
-                    body = self._request_ajax("/illust/" + str(work["id"]))
-                    return self._extract_ajax(work, body)
-                else:
-                    self.log.warning(
-                        "%s: Unable to download work ('sanity_level' warning)",
-                        work["id"])
-            elif url == self.mypixiv_url:
-                work["_mypixiv"] = True
-                self.log.warning("%s: 'My pixiv' locked", work["id"])
-                return ()
-            else:
-                return ({"url": url},)
-
-        else:
+        if meta_pages:
             return [
                 {
                     "url"   : img["image_urls"]["original"],
@@ -141,30 +115,58 @@ class PixivExtractor(Extractor):
                 for num, img in enumerate(meta_pages)
             ]
 
+        url = meta_single_page["original_image_url"]
+        if url == self.sanity_url:
+            work["_ajax"] = True
+            self.log.warning("%s: 'limit_sanity_level' warning", work["id"])
+            if self.sanity_workaround:
+                body = self._request_ajax("/illust/" + str(work["id"]))
+                return self._extract_ajax(work, body)
+
+        elif url == self.mypixiv_url:
+            work["_mypixiv"] = True
+            self.log.warning("%s: 'My pixiv' locked", work["id"])
+
+        elif work["type"] != "ugoira":
+            return ({"url": url},)
+
+        elif self.load_ugoira:
+            try:
+                return self._extract_ugoira(work, url)
+            except Exception as exc:
+                self.log.warning(
+                    "%s: Unable to retrieve Ugoira metatdata (%s - %s)",
+                    work["id"], exc.__class__.__name__, exc)
+
         return ()
 
-    def _extract_ugoira(self, work):
+    def _extract_ugoira(self, work, img_url):
         ugoira = self.api.ugoira_metadata(work["id"])
-        url = ugoira["zip_urls"]["medium"]
         work["_ugoira_frame_data"] = work["frames"] = frames = ugoira["frames"]
-        work["date_url"] = self._date_from_url(url)
+        work["_ugoira_original"] = self.load_ugoira_original
         work["_http_adjust_extension"] = False
 
-        if self.load_ugoira == "original":
-            work["_ugoira_original"] = True
-            base, sep, _ = url.rpartition("_ugoira")
-            base = base.replace("/img-zip-ugoira/", "/img-original/", 1) + sep
+        if self.load_ugoira_original:
+            work["date_url"] = self._date_from_url(img_url)
 
-            for ext in ("jpg", "png", "gif"):
-                try:
-                    url = "{}0.{}".format(base, ext)
-                    self.request(url, method="HEAD")
-                    break
-                except exception.HttpError:
-                    pass
+            base, sep, ext = img_url.rpartition("_ugoira0.")
+            if sep:
+                base += "_ugoira"
             else:
-                self.log.warning(
-                    "Unable to find Ugoira frame URLs (%s)", work["id"])
+                base, sep, _ = img_url.rpartition("_ugoira")
+                base = base.replace(
+                    "/img-zip-ugoira/", "/img-original/", 1) + sep
+
+                for ext in ("jpg", "png", "gif"):
+                    try:
+                        url = "{}0.{}".format(base, ext)
+                        self.request(url, method="HEAD")
+                        break
+                    except exception.HttpError:
+                        pass
+                else:
+                    self.log.warning(
+                        "Unable to find Ugoira frame URLs (%s)", work["id"])
 
             return [
                 {
@@ -174,9 +176,11 @@ class PixivExtractor(Extractor):
                 }
                 for num in range(len(frames))
             ]
+
         else:
-            work["_ugoira_original"] = False
-            url = url.replace("_ugoira600x600", "_ugoira1920x1080", 1)
+            zip_url = ugoira["zip_urls"]["medium"]
+            work["date_url"] = self._date_from_url(zip_url)
+            url = zip_url.replace("_ugoira600x600", "_ugoira1920x1080", 1)
             return ({"url": url},)
 
     def _request_ajax(self, endpoint):
@@ -333,12 +337,12 @@ class PixivUserExtractor(PixivExtractor):
 class PixivArtworksExtractor(PixivExtractor):
     """Extractor for artworks of a pixiv user"""
     subcategory = "artworks"
-    _warning = True
     pattern = (BASE_PATTERN + r"/(?:"
                r"(?:en/)?users/(\d+)/(?:artworks|illustrations|manga)"
                r"(?:/([^/?#]+))?/?(?:$|[?#])"
                r"|member_illust\.php\?id=(\d+)(?:&([^#]+))?)")
     example = "https://www.pixiv.net/en/users/12345/artworks"
+    _warn_phpsessid = True
 
     def _init(self):
         PixivExtractor._init(self)
@@ -352,12 +356,13 @@ class PixivArtworksExtractor(PixivExtractor):
         self.tag = t1 or t2
 
         if self.sanity_workaround:
-            self.cookies_domain = d = ".pixiv.net"
+            self.cookies_domain = domain = ".pixiv.net"
             self._init_cookies()
-            if self._warning and not self.cookies.get("PHPSESSID", domain=d):
-                PixivArtworksExtractor._warning = False
-                self.log.warning("No 'PHPSESSID' cookie set. Can detect only "
-                                 "non R-18 'sanity_level' works.")
+            if self._warn_phpsessid:
+                PixivArtworksExtractor._warn_phpsessid = False
+                if not self.cookies.get("PHPSESSID", domain=domain):
+                    self.log.warning("No 'PHPSESSID' cookie set. Can detect on"
+                                     "ly non R-18 'limit_sanity_level' works.")
 
     def metadata(self):
         if self.config("metadata"):
@@ -601,7 +606,10 @@ class PixivRankingExtractor(PixivExtractor):
         self.mode = self.date = None
 
     def works(self):
-        return self.api.illust_ranking(self.mode, self.date)
+        ranking = self.ranking
+        for ranking["rank"], work in enumerate(
+                self.api.illust_ranking(self.mode, self.date), 1):
+            yield work
 
     def metadata(self):
         query = text.parse_query(self.query)
@@ -640,10 +648,12 @@ class PixivRankingExtractor(PixivExtractor):
             date = (now - timedelta(days=1)).strftime("%Y-%m-%d")
         self.date = date
 
-        return {"ranking": {
+        self.ranking = ranking = {
             "mode": mode,
             "date": self.date,
-        }}
+            "rank": 0,
+        }
+        return {"ranking": ranking}
 
 
 class PixivSearchExtractor(PixivExtractor):
@@ -734,7 +744,6 @@ class PixivPixivisionExtractor(PixivExtractor):
     directory_fmt = ("{category}", "pixivision",
                      "{pixivision_id} {pixivision_title}")
     archive_fmt = "V{pixivision_id}_{id}{suffix}.{extension}"
-    cookies_domain = ".pixiv.net"
     pattern = r"(?:https?://)?(?:www\.)?pixivision\.net/(?:en/)?a/(\d+)"
     example = "https://www.pixivision.net/en/a/12345"