import subprocess
import logging
from urllib import urlencode
from urlparse import parse_qs, urlsplit, urlunsplit
from bs4 import BeautifulSoup
logger = logging.getLogger(__name__)
def set_query_parameter(url, param_name, param_value):
# From: http://stackoverflow.com/questions/4293460/how-to-add-custom-parameters-to-an-url-query-string-with-python
scheme, netloc, path, query_string, fragment = urlsplit(url)
query_params = parse_qs(query_string)
query_params[param_name] = [param_value]
new_query_string = urlencode(query_params, doseq=True)
return urlunsplit((scheme, netloc, path, new_query_string, fragment))
def render_snapshot(url):
logger.info('Snapshotting url: %s' % url)
url = set_query_parameter(url, 'use_cdn', False)
out_html = subprocess.check_output(['phantomjs', '--ignore-ssl-errors=yes',
'--disk-cache=yes', '--ssl-protocol=tlsv1',
'util/phantomjs-runner.js', url])
if not out_html or out_html.strip() == 'Not Found':
return None
# Remove script tags
logger.info('Removing script tags: %s' % url)
try:
soup = BeautifulSoup(out_html.decode('utf8'), 'html.parser')
to_extract = soup.findAll('script')
for item in to_extract:
item.extract()
except:
logger.exception('Exception when trying to parse served HTML')
return out_html
return str(soup)