Home Explore Help
Sign In
software
/
archival.ArchiveBox
mirror of https://github.com/ArchiveBox/ArchiveBox.git
2
0
Fork 0
Files Issues 0 Wiki
Browse Source

feat: Add html export to list command

Cristian 5 years ago
parent
aab8f96520
commit
885ff50449
6 changed files with 56 additions and 4 deletions
Unified View Show Diff Stats
  1. 6 0
      archivebox/cli/archivebox_list.py
  2. 3 2
      archivebox/index/html.py
  3. 9 1
      archivebox/logging_util.py
  4. 2 1
      archivebox/main.py
  5. 20 0
      archivebox/themes/legacy/main_index_minimal.html
  6. 16 0
      tests/test_list.py

+ 6 - 0
archivebox/cli/archivebox_list.py
View File 

@@ -46,6 +46,11 @@ def main(args: Optional[List[str]]=None, stdin: Optional[IO]=None, pwd: Optional
 
         action='store_true',
 
         action='store_true',
 
         help="Print the output in JSON format with all columns included.",
 
         help="Print the output in JSON format with all columns included.",
 
     )
 
     )
 
+    group.add_argument(
 
+        '--html',
 
+        action='store_true',
 
+        help="Print the output in HTML format"
 
+    )
 
     parser.add_argument(
 
     parser.add_argument(
 
         '--index',
 
         '--index',
 
         action='store_true',
 
         action='store_true',
 
@@ -117,6 +122,7 @@ def main(args: Optional[List[str]]=None, stdin: Optional[IO]=None, pwd: Optional
 
         sort=command.sort,
 
         sort=command.sort,
 
         csv=command.csv,
 
         csv=command.csv,
 
         json=command.json,
 
         json=command.json,
 
+        html=command.html,
 
         index=command.index,
 
         index=command.index,
 
         out_dir=pwd or OUTPUT_DIR,
 
         out_dir=pwd or OUTPUT_DIR,
 
     )
 
     )

+ 3 - 2
archivebox/index/html.py
View File 

@@ -31,6 +31,7 @@ from ..config import (
 
 
 
 join = lambda *paths: os.path.join(*paths)
 
 join = lambda *paths: os.path.join(*paths)
 
 MAIN_INDEX_TEMPLATE = join(TEMPLATES_DIR, 'main_index.html')
 
 MAIN_INDEX_TEMPLATE = join(TEMPLATES_DIR, 'main_index.html')
 
+MINIMAL_INDEX_TEMPLATE = join(TEMPLATES_DIR, 'main_index_minimal.html')
 
 MAIN_INDEX_ROW_TEMPLATE = join(TEMPLATES_DIR, 'main_index_row.html')
 
 MAIN_INDEX_ROW_TEMPLATE = join(TEMPLATES_DIR, 'main_index_row.html')
 
 LINK_DETAILS_TEMPLATE = join(TEMPLATES_DIR, 'link_details.html')
 
 LINK_DETAILS_TEMPLATE = join(TEMPLATES_DIR, 'link_details.html')
 
 TITLE_LOADING_MSG = 'Not yet archived...'
 
 TITLE_LOADING_MSG = 'Not yet archived...'
 
@@ -63,10 +64,10 @@ def write_html_main_index(links: List[Link], out_dir: str=OUTPUT_DIR, finished:
 
 
 
 
 
 @enforce_types
 
 @enforce_types
 
-def main_index_template(links: List[Link], finished: bool=True) -> str:
 
+def main_index_template(links: List[Link], finished: bool=True, template: str=MAIN_INDEX_TEMPLATE) -> str:
 
     """render the template for the entire main index"""
 
     """render the template for the entire main index"""
 
 
 
-    return render_legacy_template(MAIN_INDEX_TEMPLATE, {
 
+    return render_legacy_template(template, {
 
         'version': VERSION,
 
         'version': VERSION,
 
         'git_sha': GIT_SHA,
 
         'git_sha': GIT_SHA,
 
         'num_links': str(len(links)),
 
         'num_links': str(len(links)),

+ 9 - 1
archivebox/logging_util.py
View File 

@@ -462,6 +462,7 @@ def printable_filesize(num_bytes: Union[int, float]) -> str:
 
 @enforce_types
 
 @enforce_types
 
 def printable_folders(folders: Dict[str, Optional["Link"]],
 
 def printable_folders(folders: Dict[str, Optional["Link"]],
 
                       json: bool=False,
 
                       json: bool=False,
 
+                      html: bool=False,
 
                       csv: Optional[str]=None,
 
                       csv: Optional[str]=None,
 
                       index: bool=False) -> str:
 
                       index: bool=False) -> str:
 
     links = folders.values()
 
     links = folders.values()
 
@@ -478,7 +479,14 @@ def printable_folders(folders: Dict[str, Optional["Link"]],
 
         else:
 
         else:
 
             output = links
 
             output = links
 
         return to_json(output, indent=4, sort_keys=True)
 
         return to_json(output, indent=4, sort_keys=True)
 
-
 
+    elif html:
 
+        from .index.html import main_index_template
 
+        if index:
 
+            output = main_index_template(links, True)
 
+        else:
 
+            from .index.html import MINIMAL_INDEX_TEMPLATE
 
+            output = main_index_template(links, True, MINIMAL_INDEX_TEMPLATE)
 
+        return output
 
     elif csv:
 
     elif csv:
 
         from .index.csv import links_to_csv
 
         from .index.csv import links_to_csv
 
         return links_to_csv(folders.values(), cols=csv.split(','), header=True)
 
         return links_to_csv(folders.values(), cols=csv.split(','), header=True)

+ 2 - 1
archivebox/main.py
View File 

@@ -730,6 +730,7 @@ def list_all(filter_patterns_str: Optional[str]=None,
 
              sort: Optional[str]=None,
 
              sort: Optional[str]=None,
 
              csv: Optional[str]=None,
 
              csv: Optional[str]=None,
 
              json: bool=False,
 
              json: bool=False,
 
+             html: bool=False,
 
              index: bool=False,
 
              index: bool=False,
 
              out_dir: str=OUTPUT_DIR) -> Iterable[Link]:
 
              out_dir: str=OUTPUT_DIR) -> Iterable[Link]:
 
     """List, filter, and export information about archive entries"""
 
     """List, filter, and export information about archive entries"""
 
@@ -763,7 +764,7 @@ def list_all(filter_patterns_str: Optional[str]=None,
 
         out_dir=out_dir,
 
         out_dir=out_dir,
 
     )
 
     )
 
     
     
-    print(printable_folders(folders, json=json, csv=csv, index=index))
 
+    print(printable_folders(folders, json=json, csv=csv, html=html, index=index))
 
     return folders
 
     return folders

+ 20 - 0
archivebox/themes/legacy/main_index_minimal.html
View File 

@@ -0,0 +1,20 @@
 
+<!DOCTYPE html>
 
+<html lang="en">
 
+    <head>
 
+        <title>Archived Sites</title>
 
+        <meta charset="utf-8" name="viewport" content="width=device-width, initial-scale=1">
 
+    </head>
 
+    <body data-status="$status">
 
+        <table id="table-bookmarks">
 
+            <thead>
 
+                <tr class="thead-tr">
 
+                    <th style="width: 100px;">Bookmarked</th>
 
+                    <th style="width: 26vw;">Saved Link ($num_links)</th>
 
+                    <th style="width: 50px">Files</th>
 
+                    <th style="width: 16vw;whitespace:nowrap;overflow-x:hidden;">Original URL</th>
 
+                </tr>
 
+            </thead>
 
+            <tbody>$rows</tbody>
 
+        </table>
 
+    </body>
 
+</html>

+ 16 - 0
tests/test_list.py
View File 

@@ -16,3 +16,19 @@ def test_list_json_index(process, disable_extractors_dict):
 
     list_process = subprocess.run(["archivebox", "list", "--json", "--index"], capture_output=True)
 
     list_process = subprocess.run(["archivebox", "list", "--json", "--index"], capture_output=True)
 
     output_json = json.loads(list_process.stdout.decode("utf-8"))
 
     output_json = json.loads(list_process.stdout.decode("utf-8"))
 
     assert output_json["links"][0]["url"] == "http://127.0.0.1:8080/static/example.com.html"
 
     assert output_json["links"][0]["url"] == "http://127.0.0.1:8080/static/example.com.html"
 
+
 
+def test_list_html(process, disable_extractors_dict):
 
+    subprocess.run(["archivebox", "add", "http://127.0.0.1:8080/static/example.com.html", "--depth=0"],
 
+                                  capture_output=True, env=disable_extractors_dict)
 
+    list_process = subprocess.run(["archivebox", "list", "--html"], capture_output=True)
 
+    output_html = list_process.stdout.decode("utf-8")
 
+    assert "<footer>" not in output_html
 
+    assert "http://127.0.0.1:8080/static/example.com.html" in output_html
 
+
 
+def test_list_html_index(process, disable_extractors_dict):
 
+    subprocess.run(["archivebox", "add", "http://127.0.0.1:8080/static/example.com.html", "--depth=0"],
 
+                                  capture_output=True, env=disable_extractors_dict)
 
+    list_process = subprocess.run(["archivebox", "list", "--html", "--index"], capture_output=True)
 
+    output_html = list_process.stdout.decode("utf-8")
 
+    assert "<footer>" in output_html
 
+    assert "http://127.0.0.1:8080/static/example.com.html" in output_html