Remove query strings from file:// URIs

liZe · liZe · commit 40f4e9af4c11 · 2018-10-26T19:18:33.000+02:00
Fix #687, fix #688.
diff --git a/weasyprint/tests/test_api.py b/weasyprint/tests/test_api.py
@@ -799,7 +799,8 @@ def assert_links(html, expected_links_by_page, expected_anchors_by_page,
 
 @assert_no_logs
 def test_url_fetcher():
-    with open(resource_filename('pattern.png'), 'rb') as pattern_fd:
+    filename = resource_filename('pattern.png')
+    with open(filename, 'rb') as pattern_fd:
         pattern_png = pattern_fd.read()
 
     def fetcher(url):
@@ -822,6 +823,8 @@ def test(html, blank=False):
         check_png_pattern(html.write_png(stylesheets=[css]), blank=blank)
 
     test('<body><img src="pattern.png">')  # Test a "normal" URL
+    test('<body><img src="%s">' % Path(filename).as_uri())
+    test('<body><img src="%s?ignored">' % Path(filename).as_uri())
     test('<body><img src="weasyprint-custom:foo/é_%e9_pattern">')
     test('<body style="background: url(weasyprint-custom:foo/é_%e9_pattern)">')
     test('<body><li style="list-style: inside '
diff --git a/weasyprint/urls.py b/weasyprint/urls.py
@@ -232,6 +232,10 @@ def default_url_fetcher(url, timeout=10):
 
     """
     if UNICODE_SCHEME_RE.match(url):
+        # See https://bugs.python.org/issue34702
+        if url.startswith('file://'):
+            url = url.split('?')[0]
+
         url = iri_to_uri(url)
         response = urlopen(Request(url, headers=HTTP_HEADERS), timeout=timeout)
         response_info = response.info()
