Merge pull request #1205 from Curita/htmlparser-deprecation

[MRG+1] Deprecate htmlparser link extractor

scrapy/linkextractors/htmlparser.py

@@ -2,6 +2,7 @@
 HTMLParser-based link extractor
 """
 
+import warnings
 from HTMLParser import HTMLParser
 from six.moves.urllib.parse import urljoin
 
@@ -9,12 +10,20 @@ from w3lib.url import safe_url_string
 
 from scrapy.link import Link
 from scrapy.utils.python import unique as unique_list
+from scrapy.exceptions import ScrapyDeprecationWarning
+
 
 class HtmlParserLinkExtractor(HTMLParser):
 
     def __init__(self, tag="a", attr="href", process=None, unique=False):
         HTMLParser.__init__(self)
 
+        warnings.warn(
+            "HtmlParserLinkExtractor is deprecated and will be removed in "
+            "future releases. Please use scrapy.linkextractors.LinkExtractor",
+            ScrapyDeprecationWarning, stacklevel=2,
+        )
+
         self.scan_tag = tag if callable(tag) else lambda t: t == tag
         self.scan_attr = attr if callable(attr) else lambda a: a == attr
         self.process_attr = process if callable(process) else lambda v: v

scrapy/linkextractors/sgml.py

@@ -21,7 +21,7 @@ class BaseSgmlLinkExtractor(SGMLParser):
         warnings.warn(
             "BaseSgmlLinkExtractor is deprecated and will be removed in future releases. "
             "Please use scrapy.linkextractors.LinkExtractor",
-            ScrapyDeprecationWarning
+            ScrapyDeprecationWarning, stacklevel=2,
         )
         SGMLParser.__init__(self)
         self.scan_tag = tag if callable(tag) else lambda t: t == tag
@@ -104,7 +104,7 @@ class SgmlLinkExtractor(FilteringLinkExtractor):
         warnings.warn(
             "SgmlLinkExtractor is deprecated and will be removed in future releases. "
             "Please use scrapy.linkextractors.LinkExtractor",
-            ScrapyDeprecationWarning
+            ScrapyDeprecationWarning, stacklevel=2,
         )
 
         tags, attrs = set(arg_to_iter(tags)), set(arg_to_iter(attrs))