feat: Add initial support for singlefile extractor

archivebox/extractors/__init__.py

@@ -25,6 +25,7 @@ from ..logging_util import (
 from .title import should_save_title, save_title
 from .favicon import should_save_favicon, save_favicon
 from .wget import should_save_wget, save_wget
+from .singlefile import should_save_singlefile, save_singlefile
 from .pdf import should_save_pdf, save_pdf
 from .screenshot import should_save_screenshot, save_screenshot
 from .dom import should_save_dom, save_dom
@@ -37,6 +38,7 @@ def get_default_archive_methods():
             ('title', should_save_title, save_title),
             ('favicon', should_save_favicon, save_favicon),
             ('wget', should_save_wget, save_wget),
+            ('singlefile', should_save_singlefile, save_singlefile),
             ('pdf', should_save_pdf, save_pdf),
             ('screenshot', should_save_screenshot, save_screenshot),
             ('dom', should_save_dom, save_dom),

archivebox/extractors/singlefile.py

@@ -0,0 +1,81 @@
+__package__ = 'archivebox.extractors'
+
+import os
+from pathlib import Path
+
+from typing import Optional
+
+from ..index.schema import Link, ArchiveResult, ArchiveError
+from ..system import run, chmod_file
+from ..util import (
+    enforce_types,
+)
+from ..config import (
+    TIMEOUT,
+    SAVE_SINGLEFILE,
+    SINGLEFILE_BINARY,
+    SINGLEFILE_VERSION,
+    CHROME_BINARY,
+)
+from ..logging_util import TimedProgress
+
+
+@enforce_types
+def should_save_singlefile(link: Link, out_dir: Optional[str]=None) -> bool:
+    out_dir = out_dir or link.link_dir
+    if not os.path.exists(out_dir):
+        return False
+
+    return SAVE_SINGLEFILE
+
+
+@enforce_types
+def save_singlefile(link: Link, out_dir: Optional[str]=None, timeout: int=TIMEOUT) -> ArchiveResult:
+    """download full site using single-file"""
+
+    out_dir = out_dir or link.link_dir
+    output = str(Path(out_dir).absolute() / "single-file.html")
+
+    # WGET CLI Docs: https://www.gnu.org/software/wget/manual/wget.html
+    cmd = [
+        SINGLEFILE_BINARY,
+        '--browser-executable-path={}'.format(CHROME_BINARY),
+        link.url,
+        output
+    ]
+
+    status = 'succeeded'
+    timer = TimedProgress(timeout, prefix='      ')
+    try:
+        result = run(cmd, cwd=out_dir, timeout=timeout)
+
+        # parse out number of files downloaded from last line of stderr:
+        #  "Downloaded: 76 files, 4.0M in 1.6s (2.52 MB/s)"
+        output_tail = [
+            line.strip()
+            for line in (result.stdout + result.stderr).decode().rsplit('\n', 3)[-3:]
+            if line.strip()
+        ]
+        hints = (
+            'Got single-file response code: {}.'.format(result.returncode),
+            *output_tail,
+        )
+
+        # Check for common failure cases
+        if (result.returncode > 0):
+            raise ArchiveError('SingleFile was not able to archive the page', hints)
+        chmod_file(output)
+    except Exception as err:
+        status = 'failed'
+        output = err
+    finally:
+        timer.end()
+
+    return ArchiveResult(
+        cmd=cmd,
+        pwd=out_dir,
+        cmd_version=SINGLEFILE_VERSION,
+        output=output,
+        status=status,
+        **timer.stats,
+    )