feat(convert): devine les logos et les récupère

drupal2spip_lal/base/convert.py

@@ -1,9 +1,12 @@
+import os
 import re
 from datetime import datetime
 from itertools import groupby
 
-from django.utils.timezone import make_aware, now
+from django.conf import settings
+from django.utils.timezone import make_aware
 
+import request
 from bs4 import BeautifulSoup as bs
 
 from drupal2spip_lal.drupal import models as drupal
@@ -50,6 +53,47 @@ def strong_to_dl(html):
     return '\n'.join(r)
 
 
+def fetch_and_remove_logo(article):
+    def fetch_logo(src):
+        """
+        SPIP gère les logos à la façon d'un hack : un fichier dans IMG nommé
+        'arton{}.{}'.format(article.pk, ext)
+        """
+        ext = src.split('.')[-1]
+        filename = 'arton{}.{}'.format(article.pk, ext)
+        path = os.path.join(settings.SPIP_LOGO_DIR, filename)
+
+        r = request.get(src, stream=True)
+
+        with open(path, 'wb') as fd:
+            for chunk in r.iter_content(chunk_size=128):
+                fd.write(chunk)
+
+    def remove_img(img):
+        has_siblings = [
+            elem
+            for elem in list(img.previous_siblings) + list(img.next_siblings)
+            if elem != '\n'
+        ]
+        if img.parent.name == 'a' and not has_siblings:
+            img = img.parent
+        img.replace_with('')
+
+    soup = bs(article.descriptif, 'html.parser')
+    img = soup.find('img')
+
+    src = img and img.attrs.get('src', None)
+
+    if src and src.startswith('/'):
+        src = 'http://{}{}'.format(settings.DRUPAL_FQDN, src)
+
+    if src and re.match(r'^(https?)?://', src):
+        fetch_logo(src)
+        remove_img(img)
+        article.descriptif = soup.prettify(formatter="html5")
+        article.save()
+
+
 def sanitarize_html(html):
     html = strong_to_dl(html)
     soup = bs(html, 'html.parser')
@@ -116,6 +160,7 @@ def convert_node(node, update=False):
             'en_ligne': convert_timestamp(node.user.access),
             'maj': convert_timestamp(node.user.created),
         }
+
         auteur, _ = spip.Auteurs.objects.update_or_create(
             login=node.user.name, defaults=user_attributes
         )
@@ -123,3 +168,5 @@ def convert_node(node, update=False):
         spip.AuteursLiens.objects.update_or_create(
             auteur=auteur, id_objet=article.pk, objet='article'
         )
+
+        fetch_and_remove_logo(article)

drupal2spip_lal/settings/base.py

@@ -177,6 +177,8 @@ STATICFILES_FINDERS = [
 # https://docs.djangoproject.com/en/stable/ref/settings/#media-root
 MEDIA_ROOT = var_dir('media')
 
+SPIP_LOGO_DIR = env('SPIP_LOGO_DIR', default=MEDIA_ROOT)
+
 # https://docs.djangoproject.com/en/stable/ref/settings/#media-url
 MEDIA_URL = os.path.join(APP_LOCATION, 'media/')
 
@@ -249,3 +251,5 @@ CSRF_COOKIE_PATH = APP_LOCATION
 # ------------------------------------------------------------------------------
 # APPLICATION AND 3RD PARTY LIBRARY SETTINGS
 # ------------------------------------------------------------------------------
+
+DRUPAL_FQDN = env('DRUPAL_FQDN', default='www.april.org')

requirements/base.txt

@@ -9,4 +9,5 @@ phpserialize
 
 # HTML
 # ------------------------------------------------------------------------------
+request
 beautifulsoup4