def parse_item(self, response):
# skip review pages, which are hard to distinguish from recipe pages
# in the link extractor regex
if response.url.endswith('/review'):
return []
hxs = HtmlXPathSelector(response)
raw_recipes = parse_recipes(hxs, {'source': self.source})
for recipe in raw_recipes:
if 'photo' in recipe:
recipe['photo'] = flatten(recipe['photo'])
if 'image' in recipe:
recipe['image'] = flatten(recipe['image'])
return [RecipeItem.from_dict(recipe) for recipe in raw_recipes]
def parse_item(self, response):
# skip review pages, which are hard to distinguish from recipe pages
# in the link extractor regex
if response.url.endswith('/review'):
return []
hxs = HtmlXPathSelector(response)
raw_recipes = parse_recipes(hxs, {'source': self.source})
for recipe in raw_recipes:
if 'photo' in recipe:
recipe['photo'] = flatten(recipe['photo'])
if 'image' in recipe:
recipe['image'] = flatten(recipe['image'])
return [RecipeItem.from_dict(recipe) for recipe in raw_recipes]
def parse_item(self, response):
# skip review pages, which are hard to distinguish from recipe pages
# in the link extractor regex
if '/reviews/' in response.url:
return []
hxs = HtmlXPathSelector(response)
raw_recipes = parse_recipes(hxs, {'source': self.source, 'url': response.url})
for recipe in raw_recipes:
if 'photo' in recipe:
recipe['photo'] = flatten(recipe['photo'])
recipe['photo'] = recipe['photo'].replace('_med.', '_lg.')
if 'image' in recipe:
recipe['image'] = flatten(recipe['image'])
recipe['image'] = recipe['image'].replace('_med.', '_lg.')
return [RecipeItem.from_dict(recipe) for recipe in raw_recipes]
def parse_item(self, response):
# skip review pages, which are hard to distinguish from recipe pages
# in the link extractor regex
if '/reviews/' in response.url:
return []
hxs = HtmlXPathSelector(response)
raw_recipes = parse_recipes(hxs, {'source': self.source, 'url': response.url})
for recipe in raw_recipes:
if 'photo' in recipe:
recipe['photo'] = flatten(recipe['photo'])
recipe['photo'] = recipe['photo'].replace('_med.', '_lg.')
if 'image' in recipe:
recipe['image'] = flatten(recipe['image'])
recipe['image'] = recipe['image'].replace('_med.', '_lg.')
return [RecipeItem.from_dict(recipe) for recipe in raw_recipes]
def parse_item(self, response):
hxs = HtmlXPathSelector(response)
raw_recipes = self.parse_recipes(hxs, {'source': self.source, 'url': response.url})
for recipe in raw_recipes:
if 'photo' in recipe:
photo_url = flatten(recipe['photo'])
if photo_url.startswith('//'):
photo_url = 'http:' + photo_url
recipe['photo'] = photo_url
if 'image' in recipe:
photo_url = flatten(recipe['image'])
if photo_url.startswith('//'):
photo_url = 'http:' + photo_url
recipe['image'] = photo_url
return [RecipeItem.from_dict(recipe) for recipe in raw_recipes]
def parse_item(self, response):
hxs = HtmlXPathSelector(response)
raw_recipes = self.parse_recipes(hxs, {
'source': self.source,
'url': response.url
})
for recipe in raw_recipes:
if 'photo' in recipe:
photo_url = flatten(recipe['photo'])
if photo_url.startswith('//'):
photo_url = 'http:' + photo_url
recipe['photo'] = photo_url
if 'image' in recipe:
photo_url = flatten(recipe['image'])
if photo_url.startswith('//'):
photo_url = 'http:' + photo_url
recipe['image'] = photo_url
return [RecipeItem.from_dict(recipe) for recipe in raw_recipes]
