media normalized

migration/export.py

@@ -4,7 +4,7 @@ from datetime import datetime, timezone
 
 import frontmatter
 
-from .extract import extract_html, prepare_html_body
+from .extract import extract_html, prepare_html_body, extract_media
 from .utils import DateTimeEncoder
 
 OLD_DATE = "2016-03-05 22:22:00.350000"
@@ -50,11 +50,11 @@ def export_mdx(r):
 def export_body(shout, storage):
     entry = storage["content_items"]["by_oid"][shout["oid"]]
     if entry:
-        shout["body"], media = prepare_html_body(entry)  # prepare_md_body(entry)
+        shout["body"] = prepare_html_body(entry)  # prepare_md_body(entry)
-        shout["media"] = media
+        shout["media"] = extract_media(entry)
         export_mdx(shout)
         print("[export] html for %s" % shout["slug"])
-        body, _media = extract_html(entry)
+        body = extract_html(entry)
         open(contentDir + shout["slug"] + ".html", "w").write(body)
     else:
         raise Exception("no content_items entry found")

migration/extract.py

@@ -3,8 +3,6 @@ import os
 import re
 import uuid
 
-from .html2text import html2text
-
 TOOLTIP_REGEX = r"(\/\/\/(.+)\/\/\/)"
 contentDir = os.path.join(
     os.path.dirname(os.path.realpath(__file__)), "..", "..", "discoursio-web", "content"
@@ -258,47 +256,44 @@ def extract_md(body, oid=""):
     return newbody
 
 
-def prepare_md_body(entry):
+def extract_media(entry):
-    # body modifications
+    ''' normalized media extraction method '''
-    body = ""
+    # media [ { title pic url body } ]}
-    kind = entry.get("type")
+    kind = entry.get("layout")
-    addon = ""
+    media = []
-    if kind == "Video":
+    for m in entry.get("media", []):
-        addon = ""
+        # title
-        for m in entry.get("media", []):
+        title = m.get("title", "").replace("\n", " ").replace(" ", " ")
-            if "youtubeId" in m:
+        artist = m.get("performer") or m.get("artist")
-                addon += "<VideoPlayer youtubeId='" + m["youtubeId"] + "' />\n"
+        if artist:
+            title = artist + " - " + title
+
+        # pic
+        url = m.get("fileUrl") or m.get("url", "")
+        pic = ""
+        if "thumborId" in m:
+            pic = cdn + "/unsafe/1600x/" + m["thumborId"]
+
+        # url
+        if not url:
+            if kind == "Image":
+                url = pic
+            elif "youtubeId" in m:
+                url = "https://youtube.com/?watch=" + m["youtubeId"]
             elif "vimeoId" in m:
-                addon += "<VideoPlayer vimeoId='" + m["vimeoId"] + "' />\n"
+                url = "https://vimeo.com/" + m["vimeoId"]
             else:
                 print("[extract] media is not supported")
-                print(m)
+        # body
-        body = "import VideoPlayer from '$/components/Article/VideoPlayer'\n\n" + addon
+        body = m.get("body") or m.get("literatureBody")
 
-    elif kind == "Music":
+        media.append({
-        addon = ""
+            "url": url,
-        for m in entry.get("media", []):
+            "pic": pic,
-            artist = m.get("performer")
+            "title": title,
-            trackname = ""
+            "body": body
-            if artist:
+        })
-                trackname += artist + " - "
+    return media
-            if "title" in m:
-                trackname += m.get("title", "")
-            addon += (
-                '<AudioPlayer src="'
-                + m.get("fileUrl", "")
-                + '" title="'
-                + trackname
-                + '" />\n'
-            )
-        body = "import AudioPlayer from '$/components/Article/AudioPlayer'\n\n" + addon
-
-    body_orig, media = extract_html(entry)
-    if body_orig:
-        body += extract_md(html2text(body_orig), entry["_id"])
-    if not body:
-        print("[extract] empty MDX body")
-    return body, media
 
 
 def prepare_html_body(entry):
@@ -339,11 +334,11 @@ def prepare_html_body(entry):
             addon += '"></audio></figure>'
         body += addon
 
-    body, media = extract_html(entry)
+    body = extract_html(entry)
     # if body_orig: body += extract_md(html2text(body_orig), entry['_id'])
     if not body:
         print("[extract] empty HTML body")
-    return body, media
+    return body
 
 
 def extract_html(entry):
@@ -403,4 +398,4 @@ def extract_html(entry):
     if not body_orig:
         print("[extract] empty HTML body")
     # body_html = str(BeautifulSoup(body_orig, features="html.parser"))
-    return body_orig, media
+    return body_orig

schema.graphql

@@ -439,7 +439,7 @@ type Shout {
   deletedBy: User
   publishedBy: User
   publishedAt: DateTime
-  media: String
+  media: String # json [ { title pic url body }, .. ]
   stat: Stat
 }