mirror/archivebox
1
0
Fork 0
mirror of https://github.com/pirate/ArchiveBox.git synced 2025-08-26 07:44:41 +02:00
Code Issues Releases Wiki Activity

Adds support for HEADLESS_USER_AGENT for Chrome

Browse Source
This commit is contained in:
noncetonic
2019-03-19 05:32:48 -07:00
committed by GitHub
parent 127c72bd79
commit a13f22d15a
1 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
archivebox/archive_methods.py
View File

@@ -30,6 +30,7 @@ from config import (
SUBMIT_ARCHIVE_DOT_ORG,
COOKIES_FILE,
WGET_USER_AGENT,
HEADLESS_USER_AGENT,
CHROME_USER_DATA_DIR,
CHROME_HEADLESS,
CHROME_SANDBOX,
@@ -266,6 +267,7 @@ def fetch_pdf(link_dir, link, timeout=TIMEOUT, user_data_dir=CHROME_USER_DATA_DI
'--hide-scrollbars',
'--timeout={}'.format((timeout) * 1000),
*(() if CHECK_SSL_VALIDITY else ('--disable-web-security', '--ignore-certificate-errors')),
*(('--user-agent={}'.format(HEADLESS_USER_AGENT),) if HEADLESS_USER_AGENT else ()),
link['url']
]
end = progress(timeout, prefix=' ')
@@ -304,6 +306,7 @@ def fetch_screenshot(link_dir, link, timeout=TIMEOUT, user_data_dir=CHROME_USER_
'--hide-scrollbars',
'--timeout={}'.format((timeout) * 1000),
*(() if CHECK_SSL_VALIDITY else ('--disable-web-security', '--ignore-certificate-errors')),
*(('--user-agent={}'.format(HEADLESS_USER_AGENT),) if HEADLESS_USER_AGENT else ()),
# '--full-page', # TODO: make this actually work using ./bin/screenshot fullPage: true
link['url'],
]
@@ -342,6 +345,7 @@ def fetch_dom(link_dir, link, timeout=TIMEOUT, user_data_dir=CHROME_USER_DATA_DI
*chrome_headless(user_data_dir=user_data_dir),
'--dump-dom',
'--timeout={}'.format((timeout) * 1000),
*(('--user-agent={}'.format(HEADLESS_USER_AGENT),) if HEADLESS_USER_AGENT else ()),
link['url']
]
end = progress(timeout, prefix=' ')