def test_retrieve_error(self):
h = Haul()
with self.assertRaises(exceptions.RetrieveError):
h.find_images(self.not_exist_url)
with self.assertRaises(exceptions.RetrieveError):
h.find_images(self.broken_url)
def test_find_html_fragment(self):
h = Haul()
hr = h.find_images(self.fragmented_html)
self.assertIsInstance(hr, HaulResult)
image_urls = hr.image_urls
image_urls_count = len(image_urls)
self.assertEqual(image_urls_count, 6)
def test_find_html_fragment(self):
h = Haul()
hr = h.find_images(self.fragmented_html)
self.assertIsInstance(hr, HaulResult)
image_urls = hr.image_urls
image_urls_count = len(image_urls)
self.assertEqual(image_urls_count, 6)
def test_tumblr_image_url(self):
h = Haul()
hr = h.find_images(self.tumblr_image_url, extend=True)
self.assertIsInstance(hr, HaulResult)
self.assertIn('image/', hr.content_type)
image_urls = hr.image_urls
image_urls_count = len(image_urls)
self.assertEqual(image_urls_count, 2)
def test_tumblr_image_url(self):
h = Haul()
hr = h.find_images(self.tumblr_image_url, extend=True)
self.assertIsInstance(hr, HaulResult)
self.assertIn('image/', hr.content_type)
image_urls = hr.image_urls
image_urls_count = len(image_urls)
self.assertEqual(image_urls_count, 2)
def test_find_html_document(self):
from haul.compat import str
def img_data_src_finder(pipeline_index,
soup,
finder_image_urls=[],
*args,
**kwargs):
"""
Find image URL in <img>'s data-src attribute
"""
now_finder_image_urls = []
for img in soup.find_all('img'):
src = img.get('data-src', None)
if src:
src = str(src)
now_finder_image_urls.append(src)
output = {}
output[
'finder_image_urls'] = finder_image_urls + now_finder_image_urls
return output
FINDER_PIPELINE = (
'haul.finders.pipeline.html.img_src_finder',
'haul.finders.pipeline.html.a_href_finder',
'haul.finders.pipeline.css.background_image_finder',
img_data_src_finder,
)
h = Haul(finder_pipeline=FINDER_PIPELINE)
hr = h.find_images(self.complete_html)
self.assertIsInstance(hr, HaulResult)
test_image_url = 'http://files.heelsfetishism.com/media/heels/2013/10/03/18099_307a62430fa045cc9b2124d16de63f33.jpg'
self.assertIn(test_image_url, hr.finder_image_urls)
image_urls = hr.image_urls
image_urls_count = len(image_urls)
self.assertEqual(image_urls_count, 7)
def test_find_html_document(self):
from haul.compat import str
def img_data_src_finder(pipeline_index,
soup,
finder_image_urls=[],
*args, **kwargs):
"""
Find image URL in <img>'s data-src attribute
"""
now_finder_image_urls = []
for img in soup.find_all('img'):
src = img.get('data-src', None)
if src:
src = str(src)
now_finder_image_urls.append(src)
output = {}
output['finder_image_urls'] = finder_image_urls + now_finder_image_urls
return output
FINDER_PIPELINE = (
'haul.finders.pipeline.html.img_src_finder',
'haul.finders.pipeline.html.a_href_finder',
'haul.finders.pipeline.css.background_image_finder',
img_data_src_finder,
)
h = Haul(finder_pipeline=FINDER_PIPELINE)
hr = h.find_images(self.complete_html)
self.assertIsInstance(hr, HaulResult)
test_image_url = 'http://files.heelsfetishism.com/media/heels/2013/10/03/18099_307a62430fa045cc9b2124d16de63f33.jpg'
self.assertIn(test_image_url, hr.finder_image_urls)
image_urls = hr.image_urls
image_urls_count = len(image_urls)
self.assertEqual(image_urls_count, 7)
def test_retrieve_error(self):
h = Haul()
with self.assertRaises(exceptions.RetrieveError):
h.find_images(self.not_exist_url)
with self.assertRaises(exceptions.RetrieveError):
h.find_images(self.broken_url)
def test_wordpress(self):
h = Haul()
hr = h.find_images(self.wordpress_html, extend=True)
self.assertIsInstance(hr, HaulResult)
self.assertIn('text/html', hr.content_type)
def test_find_image_url(self):
h = Haul()
hr = h.find_images(self.image_url)
self.assertIsInstance(hr, HaulResult)
self.assertIn('image/', hr.content_type)
def test_find_image_url(self):
h = Haul()
hr = h.find_images(self.image_url)
self.assertIsInstance(hr, HaulResult)
self.assertIn('image/', hr.content_type)
def test_is_found_true(self):
h = Haul()
hr = h.find_images(self.complete_html)
self.assertTrue(hr.is_found)
def test_content_type_not_supported(self):
h = Haul()
with self.assertRaises(exceptions.ContentTypeNotSupported):
h.find_images(self.not_supported_url)
def test_invalid_parameter_error(self):
h = Haul()
with self.assertRaises(exceptions.InvalidParameterError):
url_or_html = None
h.find_images(url_or_html)
def test_wordpress(self):
h = Haul()
hr = h.find_images(self.wordpress_html, extend=True)
self.assertIsInstance(hr, HaulResult)
self.assertIn('text/html', hr.content_type)
def test_invalid_parameter_error(self):
h = Haul()
with self.assertRaises(exceptions.InvalidParameterError):
url_or_html = None
h.find_images(url_or_html)
def test_is_found_true(self):
h = Haul()
hr = h.find_images(self.complete_html)
self.assertTrue(hr.is_found)
def test_content_type_not_supported(self):
h = Haul()
with self.assertRaises(exceptions.ContentTypeNotSupported):
h.find_images(self.not_supported_url)
def test_is_found_false(self):
h = Haul()
hr = h.find_images(self.no_image_html)
self.assertFalse(hr.is_found)
def test_is_found_false(self):
h = Haul()
hr = h.find_images(self.no_image_html)
self.assertFalse(hr.is_found)
def test_find_html_url(self):
h = Haul()
hr = h.find_images(self.webpage_url)
self.assertIsInstance(hr, HaulResult)
self.assertIn('text/html', hr.content_type)
def test_find_html_url(self):
h = Haul()
hr = h.find_images(self.webpage_url)
self.assertIsInstance(hr, HaulResult)
self.assertIn('text/html', hr.content_type)
for img in soup.find_all('img'):
src = img.get('data-src', None)
if src:
src = str(src)
now_finder_image_urls.append(src)
output = {}
output['finder_image_urls'] = finder_image_urls + now_finder_image_urls
return output
MY_FINDER_PIPELINE = (
'haul.finders.pipeline.html.img_src_finder',
'haul.finders.pipeline.css.background_image_finder',
img_data_src_finder,
)
GOOGLE_SITES_EXTENDER_PIEPLINE = (
'haul.extenders.pipeline.google.blogspot_s1600_extender',
'haul.extenders.pipeline.google.ggpht_s1600_extender',
'haul.extenders.pipeline.google.googleusercontent_s1600_extender',
)
url = 'https://pixabay.com/en/photos/?q=computer&image_type=&cat=&min_width=&min_height='
h = Haul(parser='lxml',
finder_pipeline=MY_FINDER_PIPELINE,
extender_pipeline=GOOGLE_SITES_EXTENDER_PIEPLINE)
result = h.find_images(url, extend=True)
print(result)
