def generate_snapshots(base_url, overwrite=False):
urls = utils.generate_urls()
for url in urls:
# For urls that end with a trailing slash, create them
# as the index page of a subdirectory
if url and url[0] == '/':
url = url[1:]
if not url:
file_path = 'index'
file_url = ''
elif url[-1] == '/':
file_path = url + 'index'
file_url = url
else:
file_path = url
file_url = url
file_path = os.path.join(utils.HTML_DIR, file_path)
if os.path.isdir(file_path):
print 'Cannot have file_path that is directory: %s' % file_path
if not overwrite and os.path.isfile(file_path):
continue
full_url = os.path.join(base_url, file_url)
rendered_html = crawl_page(full_url)
print 'Writing: %s' % url
utils.write(file_path, rendered_html)
def generate_snapshots():
if len(sys.argv) < 2:
sys.exit('Usage: %s <server-root>' % sys.argv[0])
SERVER_ROOT = sys.argv[1]
urls = utils.generate_urls()
for url in urls:
# For urls that end with a trailing slash, create them
# as the index page of a subdirectory
if url and url[0] == '/':
url = url[1:]
if not url:
file_path = 'index'
file_url = ''
elif url[-1] == '/':
file_path = url + 'index'
file_url = url
else:
file_path = url
file_url = url
file_path = os.path.join(utils.HTML_DIR, file_path)
if os.path.isdir(file_path):
print 'Cannot have file_path that is directory: %s' % file_path
if os.path.isfile(file_path):
continue
full_url = os.path.join(SERVER_ROOT, file_url)
rendered_html = crawl_page(full_url)
print 'Writing: %s' % url
utils.write(file_path, rendered_html)
def generate_snapshots(base_url, overwrite=False):
urls = utils.generate_urls()
for url in urls:
# For urls that end with a trailing slash, create them
# as the index page of a subdirectory
if url and url[0] == '/':
url = url[1:]
if not url:
file_path = 'index'
file_url = ''
elif url[-1] == '/':
file_path = url + 'index'
file_url = url
else:
file_path = url
file_url = url
file_path = os.path.join(utils.HTML_DIR, file_path)
if os.path.isdir(file_path):
print 'Cannot have file_path that is directory: %s' % file_path
if not overwrite and os.path.isfile(file_path):
continue
full_url = os.path.join(base_url, file_url)
rendered_html = crawl_page(full_url)
print 'Writing: %s' % url
utils.write(file_path, rendered_html)
def generate_sitemap():
if len(sys.argv) < 2:
sys.exit('Usage: %s <server-root>' % sys.argv[0])
SERVER_ROOT = sys.argv[1]
relative_urls = utils.generate_urls()
full_urls = [os.path.join(SERVER_ROOT, url) for url in relative_urls]
print '\n'.join(full_urls)
def generate_sitemap():
if len(sys.argv) < 2:
sys.exit('Usage: %s <server-root>' % sys.argv[0])
SERVER_ROOT = sys.argv[1]
relative_urls = utils.generate_urls()
full_urls = [os.path.join(SERVER_ROOT, url) for url in relative_urls]
print '\n'.join(full_urls)
