mirrors/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2025-05-09 12:21:57 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

feat: Add html export to list command

Browse source
This commit is contained in:
Cristian 2020-08-19 13:02:12 -05:00 • committed by Cristian Vargas
parent aab8f96520
commit 885ff50449
6 changed files with 56 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

6
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',
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(
'--index',
action='store_true',
@ -117,6 +122,7 @@ def main(args: Optional[List[str]]=None, stdin: Optional[IO]=None, pwd: Optional
sort=command.sort,
csv=command.csv,
json=command.json,
html=command.html,
index=command.index,
out_dir=pwd or OUTPUT_DIR,
)

5
archivebox/index/html.py
View file

@ -31,6 +31,7 @@ from ..config import (
join = lambda *paths: os.path.join(*paths)
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')
LINK_DETAILS_TEMPLATE = join(TEMPLATES_DIR, 'link_details.html')
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
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"""
return render_legacy_template(MAIN_INDEX_TEMPLATE, {
return render_legacy_template(template, {
'version': VERSION,
'git_sha': GIT_SHA,
'num_links': str(len(links)),

10
archivebox/logging_util.py
View file

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

3
archivebox/main.py
View file

@ -730,6 +730,7 @@ def list_all(filter_patterns_str: Optional[str]=None,
sort: Optional[str]=None,
csv: Optional[str]=None,
json: bool=False,
html: bool=False,
index: bool=False,
out_dir: str=OUTPUT_DIR) -> Iterable[Link]:
"""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,
)
print(printable_folders(folders, json=json, csv=csv, index=index))
print(printable_folders(folders, json=json, csv=csv, html=html, index=index))
return folders

20
archivebox/themes/legacy/main_index_minimal.html Normal file
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
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)
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"
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