From 827e15b31abb71ab4c0d97fe1f7a8988a2be49e7 Mon Sep 17 00:00:00 2001
From: Nick Sweeting <git@nicksweeting.com>
Date: Fri, 11 Jan 2019 05:18:49 -0500
Subject: [PATCH] add git downloading
---
archivebox/archive_methods.py | 38 ++++++++++++++++++++++
archivebox/config.py | 1 +
archivebox/parse.py | 16 ++++-----
archivebox/templates/link_index_fancy.html | 3 +-
4 files changed, 48 insertions(+), 10 deletions(-)
diff --git a/archivebox/archive_methods.py b/archivebox/archive_methods.py
index 32bc6731..be8202c1 100644
--- a/archivebox/archive_methods.py
+++ b/archivebox/archive_methods.py
@@ -17,6 +17,7 @@ from config import (
FETCH_PDF,
FETCH_SCREENSHOT,
FETCH_DOM,
+ FETCH_GIT,
RESOLUTION,
CHECK_SSL_VALIDITY,
SUBMIT_ARCHIVE_DOT_ORG,
@@ -108,6 +109,9 @@ def archive_link(link_dir, link, overwrite=True):
# if FETCH_VIDEO:
# link = fetch_video(link_dir, link, overwrite=overwrite)
+ if FETCH_GIT:
+ link = fetch_git(link_dir, link, overwrite=overwrite)
+
if FETCH_FAVICON:
link = fetch_favicon(link_dir, link, overwrite=overwrite)
@@ -496,6 +500,40 @@ def fetch_favicon(link_dir, link, timeout=TIMEOUT):
# else:
# print(' √ Skipping video download')
+@attach_result_to_link('git')
+def fetch_git(link_dir, link, timeout=TIMEOUT):
+ """download full site using git"""
+
+ if not (link['domain'] == 'github.com'
+ or link['url'].endswith('.git')
+ or link['type'] == 'git'):
+ return
+
+ if os.path.exists(os.path.join(link_dir, 'git')):
+ return {'output': 'git', 'status': 'skipped'}
+
+ CMD = ['git', 'clone', '--recursive', link['url'], 'git']
+ output = 'git'
+
+ end = progress(timeout, prefix=' ')
+ try:
+ result = run(CMD, stdout=PIPE, stderr=PIPE, cwd=link_dir, timeout=timeout + 1) # git/<reponame>
+ end()
+
+ if result.returncode > 0:
+ print(' got git response code {}:'.format(result.returncode))
+ raise Exception('Failed git download')
+ except Exception as e:
+ end()
+ print(' Run to see full output:', 'cd {}; {}'.format(link_dir, ' '.join(CMD)))
+ print(' {}Failed: {} {}{}'.format(ANSI['red'], e.__class__.__name__, e, ANSI['reset']))
+ output = e
+
+ return {
+ 'cmd': CMD,
+ 'output': output,
+ }
+
def chrome_headless(binary=CHROME_BINARY, user_data_dir=CHROME_USER_DATA_DIR):
args = [binary, '--headless'] # '--disable-gpu'
diff --git a/archivebox/config.py b/archivebox/config.py
index 320a6a7d..9da05c66 100644
--- a/archivebox/config.py
+++ b/archivebox/config.py
@@ -21,6 +21,7 @@ FETCH_VIDEO = os.getenv('FETCH_VIDEO', 'False'
FETCH_PDF = os.getenv('FETCH_PDF', 'True' ).lower() == 'true'
FETCH_SCREENSHOT = os.getenv('FETCH_SCREENSHOT', 'True' ).lower() == 'true'
FETCH_DOM = os.getenv('FETCH_DOM', 'True' ).lower() == 'true'
+FETCH_GIT = os.getenv('FETCH_GIT', 'True' ).lower() == 'true'
FETCH_FAVICON = os.getenv('FETCH_FAVICON', 'True' ).lower() == 'true'
SUBMIT_ARCHIVE_DOT_ORG = os.getenv('SUBMIT_ARCHIVE_DOT_ORG', 'True' ).lower() == 'true'
RESOLUTION = os.getenv('RESOLUTION', '1440,1200' )
diff --git a/archivebox/parse.py b/archivebox/parse.py
index 3310f554..3fec317e 100644
--- a/archivebox/parse.py
+++ b/archivebox/parse.py
@@ -81,9 +81,9 @@ def parse_pocket_export(html_file):
'url': fixed_url,
'domain': domain(fixed_url),
'base_url': base_url(fixed_url),
- 'timestamp': str(time.timestamp()),
+ 'timestamp': str(datetime.now().timestamp()),
'tags': match.group(3),
- 'title': match.group(4).replace(' — Readability', '').replace('http://www.readability.com/read?url=', '') or base_url(fixed_url),
+ 'title': match.group(4).replace(' — Readability', '').replace('http://www.readability.com/read?url=', '') or fetch_page_title(url),
'sources': [html_file.name],
}
info['type'] = get_link_type(info)
@@ -157,7 +157,7 @@ def parse_rss_export(rss_file):
'url': url,
'domain': domain(url),
'base_url': base_url(url),
- 'timestamp': str(time.timestamp()),
+ 'timestamp': str(datetime.now().timestamp()),
'tags': '',
'title': title or fetch_page_title(url),
'sources': [rss_file.name],
@@ -184,7 +184,7 @@ def parse_bookmarks_export(html_file):
'url': url,
'domain': domain(url),
'base_url': base_url(url),
- 'timestamp': str(time.timestamp()),
+ 'timestamp': str(datetime.now().timestamp()),
'tags': "",
'title': match.group(3).strip() or fetch_page_title(url),
'sources': [html_file.name],
@@ -217,7 +217,7 @@ def parse_pinboard_rss_feed(rss_file):
'url': url,
'domain': domain(url),
'base_url': base_url(url),
- 'timestamp': str(time.timestamp()),
+ 'timestamp': str(datetime.now().timestamp()),
'tags': tags,
'title': title or fetch_page_title(url),
'sources': [rss_file.name],
@@ -242,7 +242,7 @@ def parse_medium_rss_feed(rss_file):
'url': url,
'domain': domain(url),
'base_url': base_url(url),
- 'timestamp': str(time.timestamp()),
+ 'timestamp': str(datetime.now().timestamp()),
'tags': '',
'title': title or fetch_page_title(url),
'sources': [rss_file.name],
@@ -261,13 +261,11 @@ def parse_plain_text(text_file):
urls = re.findall(URL_REGEX, line)
for url in urls:
- timestamp = str(datetime.now().timestamp())
-
info = {
'url': url,
'domain': domain(url),
'base_url': base_url(url),
- 'timestamp': timestamp,
+ 'timestamp': str(datetime.now().timestamp()),
'tags': '',
'title': fetch_page_title(url),
'sources': [text_file.name],
diff --git a/archivebox/templates/link_index_fancy.html b/archivebox/templates/link_index_fancy.html
index 8c884a9e..04f59530 100644
--- a/archivebox/templates/link_index_fancy.html
+++ b/archivebox/templates/link_index_fancy.html
@@ -186,7 +186,8 @@
<div class="col-lg-4 alert well">
Download:
<a href="index.json" title="JSON summary of archived link.">JSON</a> |
- <a href="." title="Webserver-provided index of files directory.">Files</a>
+ <a href="." title="Webserver-provided index of files directory.">Files</a> |
+ <a href="git/" title="Any git repos at the url">Git Code</a>
</div>
<hr/>
<div class="col-lg-2">