Support fetch movie metadata from bangumi.tv

scrapeflows/bangumi_movie.json

@@ -0,0 +1,106 @@
+{
+  "type": "movie",
+  "site": "bangumi.tv",
+  "steps": [
+    {
+      "doh": {
+        "host": "api.bgm.tv"
+      }
+    },
+    {
+      "http": {
+        "url": "https://api.bgm.tv/search/subject/{title}?type=2&start=0&max_results={limit}",
+        "method": "GET",
+        "headers": {
+          "User-Agent": "C5H12O5/syno-videoinfo-plugin{version} (https://github.com/C5H12O5/syno-videoinfo-plugin)"
+        },
+        "result": "metadata"
+      }
+    },
+    {
+      "collect": {
+        "source": "metadata",
+        "into": {
+          "ids": "['xp_texts', './list//id']"
+        }
+      }
+    },
+    {
+      "loop": {
+        "source": "ids",
+        "item": "id",
+        "steps": [
+          {
+            "http": {
+              "url": "https://api.bgm.tv/v0/subjects/{id}",
+              "method": "GET",
+              "headers": {
+                "User-Agent": "C5H12O5/syno-videoinfo-plugin{$parent[version]} (https://github.com/C5H12O5/syno-videoinfo-plugin)"
+              },
+              "result": "subject"
+            }
+          },
+          {
+            "collect": {
+              "source": "subject",
+              "into": {
+                "movie": {
+                  "title": "['xp_text', './name_cn']",
+                  "tagline": "['xp_text', './name']",
+                  "original_available": "['xp_text', './date']",
+                  "summary": "['xp_text', './summary']",
+                  "certificate": "",
+                  "genre": "['xp_texts', './tags//name']",
+                  "actor": [],
+                  "writer": "['re_matches', '\"key\":\"原作\",\"value\":\"([^\"]*?)\"']",
+                  "director": "['re_matches', '\"key\":\"导演\",\"value\":\"([^\"]*?)\"']",
+                  "extra": {
+                    "[plugin_id]": {
+                      "rating": {
+                        "[plugin_id]": "['xp_text', './rating//score', 'float']"
+                      },
+                      "poster": [
+                        "['xp_text', './images//large']"
+                      ],
+                      "backdrop": [
+                        "['xp_text', './images//large']"
+                      ]
+                    }
+                  }
+                },
+                "publish_date": "['xp_text', './date']",
+                "available_date": "{$parent[available]}"
+              }
+            }
+          },
+          {
+            "http": {
+              "url": "https://api.bgm.tv/v0/subjects/{id}/characters",
+              "method": "GET",
+              "headers": {
+                "User-Agent": "C5H12O5/syno-videoinfo-plugin{$parent[version]} (https://github.com/C5H12O5/syno-videoinfo-plugin)"
+              },
+              "result": "characters"
+            }
+          },
+          {
+            "collect": {
+              "source": "characters",
+              "into": {
+                "movie": {
+                  "actor": "['xp_texts', './/actors//name']"
+                }
+              }
+            }
+          },
+          {
+            "retval": {
+              "source": "movie",
+              "compare": "['publish_date', '>=', 'available_date']"
+            }
+          }
+        ]
+      }
+    }
+  ]
+}

scraper/scraper.py

@@ -58,7 +58,8 @@ def scrape(plugin_id: str) -> str:
         "available": jsoninput.get("original_available", None),
         "year": str(jsoninput.get("original_available", ""))[:4],
         "lang": language,
-        "limit": maxlimit
+        "limit": maxlimit,
+        "version": _version(plugin_id),
     }
 
     # load and execute scrape flows using multithreading
@@ -98,11 +99,25 @@ def _start(flow: "ScrapeFlow", limit: int):
         _logger.error("Failed to scrape from %s", flow.site, exc_info=True)
 
 
+def _version(plugin_id: str) -> str:
+    """Split the plugin ID to get the version."""
+    if "-" in plugin_id:
+        version = plugin_id.split("-")[-1]
+        if version != "plugin":
+            return f"/{version}"
+    return ""
+
+
 class ScrapeFlow:
     """A flow of steps to scrape video information."""
 
-    def __init__(self, site: str, steps: list, context: dict,
-                 priority: Optional[int]):
+    def __init__(
+        self,
+        site: str,
+        steps: list,
+        context: dict,
+        priority: Optional[int],
+    ):
         self.site = site
         self.steps = steps
         self.context = context