def test_html_not_quite_charset(self): element_walker = ElementWalker(css_scraper=CSSScraper(), javascript_scraper=JavaScriptScraper()) scraper = HTMLScraper(HTMLParser(), element_walker) request = Request('http://example.com/') response = Response(200, '') response.body = Body() with wpull.util.reset_file_offset(response.body): html_file_path = os.path.join(ROOT_PATH, 'testing', 'samples', 'videogame_top.htm') with open(html_file_path, 'rb') as in_file: shutil.copyfileobj(in_file, response.body) scrape_result = scraper.scrape(request, response) inline_urls = scrape_result.inline_links linked_urls = scrape_result.linked_links self.assertIn('http://example.com/copyright_2001_2006_rtype.gif', inline_urls) self.assertIn('http://www.geocities.jp/gamehouse_grindcrusher/', linked_urls)
def test_html_wrong_charset(self): element_walker = ElementWalker(css_scraper=CSSScraper(), javascript_scraper=JavaScriptScraper()) scraper = HTMLScraper(HTMLParser(), element_walker) request = Request('http://example.com/') response = Response(200, '') response.body = Body() with wpull.util.reset_file_offset(response.body): html_file_path = os.path.join(ROOT_PATH, 'testing', 'samples', 'kcna.html') with open(html_file_path, 'rb') as in_file: shutil.copyfileobj(in_file, response.body) scrape_result = scraper.scrape(request, response) inline_urls = scrape_result.inline_links linked_urls = scrape_result.linked_links self.assertEqual('utf-16-le', scrape_result.encoding) self.assertEqual( { 'http://example.com/utm/__utm.js', 'http://example.com/Knewskage.gif', 'http://example.com/Lline.gif', 'http://example.com/Sline.gif', 'http://example.com/korean01.gif', 'http://example.com/korean02.gif', 'http://example.com/english01.gif', 'http://example.com/english02.gif', 'http://example.com/Tongsinkage.gif', 'http://example.com/Knewskage.gif', }, inline_urls) self.assertEqual( { 'http://example.com/index-k.htm', 'http://example.com/index-e.htm', }, linked_urls)
def test_html_krokozyabry(self): element_walker = ElementWalker(css_scraper=CSSScraper(), javascript_scraper=JavaScriptScraper()) scraper = HTMLScraper(HTMLParser(), element_walker) request = Request('http://example.com/') response = Response(200, '') response.body = Body() response.fields['content-type'] = 'text/html; charset=KOI8-R' with wpull.util.reset_file_offset(response.body): html_file_path = os.path.join(ROOT_PATH, 'testing', 'samples', 'krokozyabry.html') with open(html_file_path, 'rb') as in_file: shutil.copyfileobj(in_file, response.body) scrape_result = scraper.scrape(request, response) inline_urls = scrape_result.inline_links linked_urls = scrape_result.linked_links self.assertEqual('koi8-r', scrape_result.encoding) self.assertEqual(set(), inline_urls) self.assertEqual({'http://example.com/Кракозябры'}, linked_urls)
def test_html_scraper_links_base_href(self): element_walker = ElementWalker( css_scraper=CSSScraper(), javascript_scraper=JavaScriptScraper()) scraper = HTMLScraper(self.get_html_parser(), element_walker) request = Request('http://example.com/') response = Response(200, 'OK') response.body = Body() with wpull.util.reset_file_offset(response.body): html_file_path = os.path.join(ROOT_PATH, 'testing', 'samples', 'basehref.html') with open(html_file_path, 'rb') as in_file: shutil.copyfileobj(in_file, response.body) scrape_result = scraper.scrape(request, response) inline_urls = scrape_result.inline_links linked_urls = scrape_result.linked_links self.assertEqual('utf-8', scrape_result.encoding) self.assertEqual({ 'http://cdn.example.com/stylesheet1.css', 'http://www.example.com/stylesheet2.css', 'http://example.com/a/stylesheet3.css', 'http://example.com/a/dir/image1.png', 'http://example.com/dir/image2.png', 'http://example.net/image3.png', 'http://example.com/dir/image4.png', }, inline_urls ) self.assertEqual({ 'http://example.com/a/' }, linked_urls )
def test_xhtml_invalid(self): element_walker = ElementWalker(css_scraper=CSSScraper(), javascript_scraper=JavaScriptScraper()) scraper = HTMLScraper(HTMLParser(), element_walker) request = Request('http://example.com/') response = Response(200, '') response.body = Body() with wpull.util.reset_file_offset(response.body): html_file_path = os.path.join(ROOT_PATH, 'testing', 'samples', 'xhtml_invalid.html') with open(html_file_path, 'rb') as in_file: shutil.copyfileobj(in_file, response.body) scrape_result = scraper.scrape(request, response) inline_urls = scrape_result.inline_links linked_urls = scrape_result.linked_links self.assertEqual( { 'http://example.com/image.png', 'http://example.com/script.js', }, inline_urls) self.assertEqual({'http://example.com/link'}, linked_urls)
def test_html_scraper_links(self): element_walker = ElementWalker(css_scraper=CSSScraper(), javascript_scraper=JavaScriptScraper()) scraper = HTMLScraper(HTMLParser(), element_walker) request = Request('http://example.com/') response = Response(200, 'OK') response.body = Body() response.fields['Refresh'] = '3; url=header_refresh.html' with wpull.util.reset_file_offset(response.body): html_file_path = os.path.join(ROOT_PATH, 'testing', 'samples', 'many_urls.html') with open(html_file_path, 'rb') as in_file: shutil.copyfileobj(in_file, response.body) scrape_result = scraper.scrape(request, response) inline_urls = scrape_result.inline_links linked_urls = scrape_result.linked_links self.assertEqual('utf-8', scrape_result.encoding) self.assertEqual( frozenset({ 'http://example.com/style_import_url.css', 'http://example.com/style_import_quote_url.css', 'http://example.com/style_single_quote_import.css', 'http://example.com/style_double_quote_import.css', 'http://example.com/bg.png', 'http://example.com/link_href.css', 'http://example.com/script.js', 'http://example.com/body_background.png', 'http://example.com/images/table_background.png', 'http://example.com/images/td_background.png', 'http://example.com/images/th_background.png', 'http://example.com/style_url1.png', 'http://example.com/style_url2.png', 'http://example.com/applet/', # returned by lxml 'http://example.com/applet/applet_code.class', 'http://example.com/applet/applet_src.class', 'http://example.com/bgsound.mid', 'http://example.com/audio_src.wav', 'http://example.com/audio_poster.jpeg', 'http://example.net/source_src.wav', 'http://example.com/video_src.webm', 'http://example.com/video_poster.jpeg', 'http://example.net/track_src.vtt', 'http://example.net/source_src.webm', 'http://example.com/embed_src.mov', 'http://example.com/fig_src.png', 'http://example.com/frame_src.html', 'http://example.com/iframe_src.html', 'http://example.com/img_href.png', 'http://example.com/img_lowsrc.png', 'http://example.com/img_src.png', 'http://example.com/img_data.png', 'http://example.com/img_srcset_1.jpeg', 'http://example.com/img_srcset_2.jpeg', 'http://example.com/img_srcset_3.jpeg', 'http://example.com/input_src.png', 'http://example.com/layer_src.png', 'http://example.com/object/', # returned by lxml 'http://example.com/object/object_data.swf', 'http://example.com/object/object_archive.dat', 'mailto:internet', 'object_not_url_codebase', 'http://example.com/param_ref_value.php', 'http://example.com/overlay_src.html', 'http://example.com/script_variable.png', }), inline_urls) self.assertEqual( frozenset({ 'http://example.com/og_image.png', 'http://example.com/og_url.html', 'http://example.com/og_audio.mp3', 'http://example.com/og_video.webm', 'http://example.com/twitter_image.png', 'http://example.com/twitter_image0.png', 'http://example.com/twitter_image1.png', 'http://example.com/twitter_image2.png', 'http://example.com/twitter_image3.png', 'http://example.com/twitter_player.html', 'http://example.com/twitter_stream.mp4', 'http://example.net/soup.html', 'http://example.com/a_href.html', 'http://example.com/area_href.html', 'http://example.com/frame_src.html', 'http://example.com/embed_href.html', 'http://example.com/embed_src.mov', 'http://example.com/form_action.html', 'http://example.com/iframe_src.html', 'http://example.com/layer_src.png', 'http://example.com/overlay_src.html', 'ftp://ftp.protocol.invalid/', 'mailto:[email protected]', 'http://a-double-slash.example', 'http://example.com/header_refresh.html', 'https://[2001:db8:85a3:8d3:1319:8a2e:370:7348]:8080/ipv6', 'http://example.com/document_write.html', 'http://example.com/http_document_write.html', 'http://example.com/http_document_write2.html', 'http://example.com/http document write.html', 'http://example.com/script_variable.html', 'http://example.com/http_script_variable.html', 'https://example.com/https_script_variable.html', 'ftp://example.com/ftp_script_variable.html', 'http://example.com/end_dir_script_variable/', 'http://example.com/start_dir_script_variable', 'http://example.com/../relative_dir_script_variable' if sys.version_info < (3, 5) else 'http://example.com/relative_dir_script_variable', 'http://example.com/script_json.html', 'http://example.com/http_script_json.html?a=b', 'http://example.com/a_javascript_link.html', 'http://example.com/a_onclick_link.html', }), linked_urls) for url in inline_urls | linked_urls: self.assertIsInstance(url, str)