mirrors/ArchiveBox
1
0
Fork 0
mirror of https://github.com/ArchiveBox/ArchiveBox.git synced 2025-05-14 15:14:31 -04:00
Code Issues Projects Releases Packages Wiki Activity Actions

handle failing screenshots and PDFs better

Browse source
This commit is contained in:
Nick Sweeting 2017-06-15 19:12:56 -05:00
parent 3957bab0e9
commit b00498dc42
1 changed files with 6 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

9
archive.py
View file

@ -141,7 +141,8 @@ def parse_bookmarks_export(html_file):
def fetch_wget(out_dir, link, overwrite=False): def fetch_wget(out_dir, link, overwrite=False):
# download full site # download full site
if not os.path.exists('{}/{}'.format(out_dir, link['base_url'].split('/', 1)[0])) or overwrite: domain = link['base_url'].split('/', 1)[0]
if not os.path.exists('{}/{}'.format(out_dir, domain)) or overwrite:
print(' - Downloading Full Site') print(' - Downloading Full Site')
CMD = [ CMD = [
*'wget --no-clobber --page-requisites --adjust-extension --convert-links --no-parent'.split(' '), *'wget --no-clobber --page-requisites --adjust-extension --convert-links --no-parent'.split(' '),
@ -161,7 +162,8 @@ def fetch_pdf(out_dir, link, overwrite=False):
chrome_args = '--headless --disable-gpu --print-to-pdf'.split(' ') chrome_args = '--headless --disable-gpu --print-to-pdf'.split(' ')
try: try:
run([CHROME_BINARY, *chrome_args, link['url']], stdout=DEVNULL, stderr=DEVNULL, cwd=out_dir, timeout=20) # output.pdf run([CHROME_BINARY, *chrome_args, link['url']], stdout=DEVNULL, stderr=DEVNULL, cwd=out_dir, timeout=20) # output.pdf
run(['chmod', ARCHIVE_PERMISSIONS, 'output.pdf'], timeout=5) if run(['chmod', ARCHIVE_PERMISSIONS, 'output.pdf'], stdout=DEVNULL, stderr=DEVNULL, timeout=5).returncode:
raise Exception('Failed to print PDF')
except Exception as e: except Exception as e:
print(' Exception: {} {}'.format(e.__class__.__name__, e)) print(' Exception: {} {}'.format(e.__class__.__name__, e))
else: else:
@ -174,7 +176,8 @@ def fetch_screenshot(out_dir, link, overwrite=False):
chrome_args = '--headless --disable-gpu --screenshot'.split(' ') chrome_args = '--headless --disable-gpu --screenshot'.split(' ')
try: try:
run([CHROME_BINARY, *chrome_args, '--window-size={}'.format(RESOLUTION), link['url']], stdout=DEVNULL, stderr=DEVNULL, cwd=out_dir, timeout=20) # sreenshot.png run([CHROME_BINARY, *chrome_args, '--window-size={}'.format(RESOLUTION), link['url']], stdout=DEVNULL, stderr=DEVNULL, cwd=out_dir, timeout=20) # sreenshot.png
run(['chmod', ARCHIVE_PERMISSIONS, 'screenshot.png'], timeout=5) if run(['chmod', ARCHIVE_PERMISSIONS, 'screenshot.png'], stdout=DEVNULL, stderr=DEVNULL, timeout=5).returncode:
raise Exception('Failed to take screenshot')
except Exception as e: except Exception as e:
print(' Exception: {} {}'.format(e.__class__.__name__, e)) print(' Exception: {} {}'.format(e.__class__.__name__, e))
else: else: