Add log print for url indexing

archivebox/search/__init__.py

@@ -8,7 +8,7 @@ from archivebox.index.schema import Link
 from archivebox.util import enforce_types
 from archivebox.config import setup_django,stderr, OUTPUT_DIR, USE_INDEXING_BACKEND, USE_SEARCHING_BACKEND, SEARCH_BACKEND_ENGINE
 
-from .utils import get_indexable_content
+from .utils import get_indexable_content, log_index_started
 
 def indexing_enabled():
     return USE_INDEXING_BACKEND
@@ -98,4 +98,5 @@ def index_links(links: Union[List[Link],None], out_dir: Path=OUTPUT_DIR):
         if snap := Snapshot.objects.filter(url=link.url).first():
             results = ArchiveResult.objects.indexable().filter(snapshot=snap)
             texts = get_indexable_content(results)
+            log_index_started(link.url)
             write_search_index(link, texts, out_dir=out_dir)

archivebox/search/utils.py

@@ -1,6 +1,11 @@
 from django.db.models import QuerySet
 
 from archivebox.util import enforce_types
+from archivebox.config import ANSI
+
+def log_index_started(url):
+    print('{green}[*] Indexing url: {} in the search index {reset}'.format(url, **ANSI))
+    print( )
 
 def get_file_result_content(res, extra_path, use_pwd=False):
     if use_pwd: 
@@ -12,7 +17,7 @@ def get_file_result_content(res, extra_path, use_pwd=False):
         fpath = f'{fpath}/{extra_path}'
 
     with open(fpath, 'r') as file:
-        data = file.read().replace('\n', '')
+        data = file.read()
     if data:
         return [data]
     return []
@@ -28,6 +33,7 @@ def get_indexable_content(results: QuerySet):
     if method not in ('readability', 'singlefile', 'dom', 'wget'):
         return []
     # This should come from a plugin interface
+
     if method == 'readability':
         return get_file_result_content(res, 'content.txt')
     elif method == 'singlefile':