use KEY, NAME, and PARSER to define parsers instead of hardcoding in init

archivebox/parsers/__init__.py

@@ -31,39 +31,41 @@ from ..util import (
 from ..index.schema import Link
 from ..logging_util import TimedProgress, log_source_saved
 
-from .pocket_html import parse_pocket_html_export
-from .pocket_api import parse_pocket_api_export
-from .pinboard_rss import parse_pinboard_rss_export
-from .wallabag_atom import parse_wallabag_atom_export
-from .shaarli_rss import parse_shaarli_rss_export
-from .medium_rss import parse_medium_rss_export
-from .netscape_html import parse_netscape_html_export
-from .generic_rss import parse_generic_rss_export
-from .generic_json import parse_generic_json_export
-from .generic_html import parse_generic_html_export
-from .generic_txt import parse_generic_txt_export
-from .url_list import parse_url_list
+from . import pocket_api
+from . import wallabag_atom
+from . import pocket_html
+from . import pinboard_rss
+from . import shaarli_rss
+from . import medium_rss
+
+from . import netscape_html
+from . import generic_rss
+from . import generic_json
+from . import generic_html
+from . import generic_txt
+from . import url_list
+
 
 PARSERS = {
     # Specialized parsers
-    'pocket-api': ('Pocket API', parse_pocket_api_export),
-    'wallabag': ('Wallabag ATOM', parse_wallabag_atom_export),
-    'pocket-html': ('Pocket HTML', parse_pocket_html_export),
-    'pinboard-rss': ('Pinboard RSS', parse_pinboard_rss_export),
-    'shaarli-rss': ('Shaarli RSS', parse_shaarli_rss_export),
-    'medium-rss': ('Medium RSS', parse_medium_rss_export),
-    
-    # General parsers
-    'netscape-html': ('Netscape HTML', parse_netscape_html_export),
-    'rss': ('Generic RSS', parse_generic_rss_export),
-    'json': ('Generic JSON', parse_generic_json_export),
-    'html': ('Generic HTML', parse_generic_html_export),
+    pocket_api.KEY:     (pocket_api.NAME,       pocket_api.PARSER),
+    wallabag_atom.KEY:  (wallabag_atom.NAME,    wallabag_atom.PARSER),
+    pocket_html.KEY:    (pocket_html.NAME,      pocket_html.PARSER),
+    pinboard_rss.KEY:   (pinboard_rss.NAME,     pinboard_rss.PARSER),
+    shaarli_rss.KEY:    (shaarli_rss.NAME,      shaarli_rss.PARSER),
+    medium_rss.KEY:     (medium_rss.NAME,       medium_rss.PARSER),
 
-    # Fallback parser
-    'plain-text': ('Plain Text', parse_generic_txt_export),
+    # General parsers
+    netscape_html.KEY:  (netscape_html.NAME,    netscape_html.PARSER),
+    generic_rss.KEY:    (generic_rss.NAME,      generic_rss.PARSER),
+    generic_json.KEY:   (generic_json.NAME,     generic_json.PARSER),
+    generic_html.KEY:   (generic_html.NAME,     generic_html.PARSER),
+
+    # Catchall fallback parser
+    generic_txt.KEY:    (generic_txt.NAME,      generic_txt.PARSER),
 
     # Explicitly specified parsers
-    'url-list': ('URL list', parse_url_list),
+    url_list.KEY:       (url_list.NAME,         url_list.PARSER),
 }
 
 

archivebox/parsers/generic_html.py

@@ -51,3 +51,8 @@ def parse_generic_html_export(html_file: IO[str], root_url: Optional[str]=None,
                     tags=None,
                     sources=[html_file.name],
                 )
+
+
+KEY = 'html'
+NAME = 'Generic HTML'
+PARSER = parse_generic_html_export

archivebox/parsers/generic_json.py

@@ -63,3 +63,8 @@ def parse_generic_json_export(json_file: IO[str], **_kwargs) -> Iterable[Link]:
                 tags=htmldecode(link.get('tags')) or '',
                 sources=[json_file.name],
             )
+
+
+KEY = 'json'
+NAME = 'Generic JSON'
+PARSER = parse_generic_json_export

archivebox/parsers/generic_rss.py

@@ -47,3 +47,8 @@ def parse_generic_rss_export(rss_file: IO[str], **_kwargs) -> Iterable[Link]:
             tags=None,
             sources=[rss_file.name],
         )
+
+
+KEY = 'rss'
+NAME = 'Generic RSS'
+PARSER = parse_generic_rss_export

archivebox/parsers/generic_txt.py

@@ -59,3 +59,7 @@ def parse_generic_txt_export(text_file: IO[str], **_kwargs) -> Iterable[Link]:
                     tags=None,
                     sources=[text_file.name],
                 )
+
+KEY = 'txt'
+NAME = 'Generic TXT'
+PARSER = parse_generic_txt_export

archivebox/parsers/medium_rss.py

@@ -33,3 +33,8 @@ def parse_medium_rss_export(rss_file: IO[str], **_kwargs) -> Iterable[Link]:
             tags=None,
             sources=[rss_file.name],
         )
+
+
+KEY = 'medium_rss'
+NAME = 'Medium RSS'
+PARSER = parse_medium_rss_export

archivebox/parsers/netscape_html.py

@@ -37,3 +37,7 @@ def parse_netscape_html_export(html_file: IO[str], **_kwargs) -> Iterable[Link]:
                 sources=[html_file.name],
             )
 
+
+KEY = 'netscape_html'
+NAME = 'Netscape HTML'
+PARSER = parse_netscape_html_export

archivebox/parsers/pinboard_rss.py

@@ -45,3 +45,8 @@ def parse_pinboard_rss_export(rss_file: IO[str], **_kwargs) -> Iterable[Link]:
             tags=htmldecode(tags) or None,
             sources=[rss_file.name],
         )
+
+
+KEY = 'pinboard_rss'
+NAME = 'Pinboard RSS'
+PARSER = parse_pinboard_rss_export

archivebox/parsers/pocket_api.py

@@ -111,3 +111,8 @@ def parse_pocket_api_export(input_buffer: IO[str], **_kwargs) -> Iterable[Link]:
                 yield link_from_article(article, sources=[line])
     
             write_since(username, api.last_since)
+
+
+KEY = 'pocket_api'
+NAME = 'Pocket API'
+PARSER = parse_pocket_api_export

archivebox/parsers/pocket_html.py

@@ -36,3 +36,8 @@ def parse_pocket_html_export(html_file: IO[str], **_kwargs) -> Iterable[Link]:
                 tags=tags or '',
                 sources=[html_file.name],
             )
+
+
+KEY = 'pocket_html'
+NAME = 'Pocket HTML'
+PARSER = parse_pocket_html_export

archivebox/parsers/shaarli_rss.py

@@ -48,3 +48,8 @@ def parse_shaarli_rss_export(rss_file: IO[str], **_kwargs) -> Iterable[Link]:
             tags=None,
             sources=[rss_file.name],
         )
+
+
+KEY = 'shaarli_rss'
+NAME = 'Shaarli RSS'
+PARSER = parse_shaarli_rss_export

archivebox/parsers/url_list.py

@@ -17,7 +17,7 @@ def parse_url_list(text_file: IO[str], **_kwargs) -> Iterable[Link]:
     text_file.seek(0)
     for line in text_file.readlines():
         url = line.strip()
-        if len(url) == 0:
+        if not url:
             continue
 
         yield Link(
@@ -27,3 +27,8 @@ def parse_url_list(text_file: IO[str], **_kwargs) -> Iterable[Link]:
             tags=None,
             sources=[text_file.name],
         )
+
+
+KEY = 'url_list'
+NAME = 'URL List'
+PARSER = parse_url_list

archivebox/parsers/wallabag_atom.py

@@ -55,3 +55,8 @@ def parse_wallabag_atom_export(rss_file: IO[str], **_kwargs) -> Iterable[Link]:
             tags=tags or '',
             sources=[rss_file.name],
         )
+
+
+KEY = 'wallabag_atom'
+NAME = 'Wallabag Atom'
+PARSER = parse_wallabag_atom_export