Skip to content

Recursively looks for urls for a given url from same host #8

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
gobelinus wants to merge 1 commit into from
Closed

Recursively looks for urls for a given url from same host #8

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
33 changes: 32 additions & 1 deletion mincss/processor.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,7 +2,7 @@
import collections
import random
import re
from urlparse import urlparse
from urlparse import urlparse, urlunparse
from lxml import etree
from lxml.cssselect import CSSSelector, SelectorSyntaxError, ExpressionError
import urllib
Expand Down Expand Up @@ -45,6 +45,7 @@ def __init__(self, debug=False):
self.inlines = []
self.links = []
self._bodies = []
self.url_queue = []

def _download(self, url):
try:
Expand Down Expand Up @@ -91,6 +92,9 @@ def process(self, *urls):

def process_url(self, url):
html = self._download(url)
if url not in self.url_queue:
self.url_queue.append(url)

self.process_html(html.strip(), url=url)

def process_html(self, html, url):
Expand Down Expand Up @@ -122,6 +126,16 @@ def process_html(self, html, url):
key = (link_url, link.attrib['href'])
self.blocks[key] = self._download(link_url)

for anchor in CSSSelector('a')(page):
link_url = self._pre_process_link(anchor.attrib['href'])
if link_url:
link_url = self._make_absolute_url(url, link_url)
if link_url \
and self._is_same_host_url(url, link_url) \
and link_url not in self.url_queue:
self.url_queue.append(link_url)
self.process_url(link_url)

def _process_content(self, content, bodies):
# Find all of the unique media queries

Expand Down Expand Up @@ -334,6 +348,23 @@ def _make_absolute_url(self, url, href):
path = '/'.join(parts)
return parsed.scheme + '://' + parsed.netloc + path

def _pre_process_link(self, link_url):
"""
should we process this link?
1. preprocess link_url and removes fragments and query parameters
2. remove javascript and mailto stuff from link_url
"""
if link_url.startswith('mailto:') \
or link_url.startswith('javascript:'):
return None
parsed = urlparse(link_url)
return urlunparse((parsed.scheme, parsed.netloc, parsed.path, parsed.params, '', ''))

def _is_same_host_url(self, url1, url2):
"""
given 2 absolute urls, test whether both have same host
"""
return (urlparse(url1).netloc == urlparse(url2).netloc)

class _Result(object):
def __init__(self, before, after):
Expand Down