本文整理汇总了Python中wpull.http.request.Response.fields['Refresh']方法的典型用法代码示例。如果您正苦于以下问题:Python Response.fields['Refresh']方法的具体用法?Python Response.fields['Refresh']怎么用?Python Response.fields['Refresh']使用的例子?那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类wpull.http.request.Response
的用法示例。
在下文中一共展示了Response.fields['Refresh']方法的4个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: test_html_soup
# 需要导入模块: from wpull.http.request import Response [as 别名]
# 或者: from wpull.http.request.Response import fields['Refresh'] [as 别名]
def test_html_soup(self):
scraper = HTMLScraper()
request = Request.new('http://example.com/')
response = Response('HTTP/1.0', 200, '')
response.fields['Refresh'] = 'yes'
with wpull.util.reset_file_offset(response.body.content_file):
html_file_path = os.path.join(os.path.dirname(__file__),
'testing', 'samples', 'soup.html')
with open(html_file_path, 'rb') as in_file:
shutil.copyfileobj(in_file, response.body.content_file)
scrape_info = scraper.scrape(request, response)
inline_urls = scrape_info['inline_urls']
linked_urls = scrape_info['linked_urls']
self.assertEqual(
{'http://example.com/ABOUTM~1.JPG'},
inline_urls
)
self.assertEqual(
{
'http://example.com/BLOG',
'http://example.com/web ring/Join.htm',
},
linked_urls
)
示例2: test_html_soup
# 需要导入模块: from wpull.http.request import Response [as 别名]
# 或者: from wpull.http.request.Response import fields['Refresh'] [as 别名]
def test_html_soup(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, '')
response.body = Body()
response.fields['Refresh'] = 'yes'
with wpull.util.reset_file_offset(response.body):
html_file_path = os.path.join(ROOT_PATH,
'testing', 'samples', 'soup.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/ABOUTM~1.JPG'},
inline_urls
)
self.assertEqual(
{
'http://example.com/BLOG',
'http://example.com/web ring/Join.htm',
},
linked_urls
)
示例3: test_html_scraper_links
# 需要导入模块: from wpull.http.request import Response [as 别名]
# 或者: from wpull.http.request.Response import fields['Refresh'] [as 别名]
def test_html_scraper_links(self):
scraper = HTMLScraper()
request = Request.new('http://example.com/')
response = Response('HTTP/1.0', 200, 'OK')
response.fields['Refresh'] = '3; url=header_refresh.html'
with wpull.util.reset_file_offset(response.body.content_file):
html_file_path = os.path.join(os.path.dirname(__file__),
'testing', 'samples',
'many_urls.html')
with open(html_file_path, 'rb') as in_file:
shutil.copyfileobj(in_file, response.body.content_file)
scrape_info = scraper.scrape(request, response)
inline_urls = scrape_info['inline_urls']
linked_urls = scrape_info['linked_urls']
self.assertEqual('ascii', scrape_info['encoding'])
self.assertEqual({
'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/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.net/source_src.wav',
'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/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',
'http://example.com/param_ref_value.php',
'http://example.com/overlay_src.html',
'http://example.com/script_variable.png',
},
inline_urls
)
self.assertEqual({
'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',
'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)
示例4: test_html_scraper_links
# 需要导入模块: from wpull.http.request import Response [as 别名]
# 或者: from wpull.http.request.Response import fields['Refresh'] [as 别名]
def test_html_scraper_links(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()
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({
'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/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.net/source_src.wav',
'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({
'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',
#.........这里部分代码省略.........