def amazon(query):
api = API(AWS_KEY, SECRET_KEY, 'us', ASSOC_TAG)
similar_root = api.similarity_lookup('B0058U6DQC', ResponseGroup='Large')
product_root = api.item_lookup('B0058U6DQC', ResponseGroup='Large')
product_root = api.item_search(title='unicorn', ResponseGroup='Large')
more_products = api.item_search('Books', Publisher='Galileo Press')
#~ from lxml import etree
#~ print etree.tostring(root, pretty_print=True)
nspace = similar_root.nsmap.get(None, '')
similar_products = similar_root.xpath('//aws:Items/aws:Item',
namespaces={'aws' : nspace})
# more_products = product_root.xpath('//aws:Items/aws:Item',
# namespaces={'aws' : nspace})
return render_template("amazon.html", similar_products=similar_products, more_products = more_products, query=query)
def amazon(query):
api = API(AWS_KEY, SECRET_KEY, 'us', ASSOC_TAG)
similar_root = api.similarity_lookup('B0058U6DQC', ResponseGroup='Large')
product_root = api.item_lookup('B0058U6DQC', ResponseGroup='Large')
product_root = api.item_search(title='unicorn', ResponseGroup='Large')
more_products = api.item_search('Books', Publisher='Galileo Press')
#~ from lxml import etree
#~ print etree.tostring(root, pretty_print=True)
nspace = similar_root.nsmap.get(None, '')
similar_products = similar_root.xpath('//aws:Items/aws:Item',
namespaces={'aws': nspace})
# more_products = product_root.xpath('//aws:Items/aws:Item',
# namespaces={'aws' : nspace})
return render_template("amazon.html",
similar_products=similar_products,
more_products=more_products,
query=query)
def getAmazonContent(query):
api = API(AWS_KEY, SECRET_KEY, 'uk', associate_tag='giracake-21', processor=minidom_response_parser)
node = api.item_search('All', Keywords=query, ResponseGroup="Medium")
products = node.getElementsByTagName('Item')
data = []
for product in products:
#print product.toprettyxml()
summaryNodes = product.getElementsByTagName('OfferSummary')
if len(summaryNodes) > 0:
for summaryNode in summaryNodes:
priceNodes = summaryNode.getElementsByTagName('LowestNewPrice')
for priceNode in priceNodes:
formattedPrice = priceNode.getElementsByTagName('FormattedPrice')
price = formattedPrice[0].childNodes[0].nodeValue
imageSetsNodes = product.getElementsByTagName('ImageSets')
if len(imageSetsNodes) > 0:
for imageSetsNode in imageSetsNodes:
imageSetNodes = imageSetsNode.getElementsByTagName('ImageSet')
for imageSetNode in imageSetNodes:
if imageSetNode.attributes["Category"].value != "primary":
continue
mediumImage = imageSetNode.getElementsByTagName('LargeImage')
url = mediumImage[0].getElementsByTagName('URL')[0]
image = url.childNodes[0].nodeValue
prod = {}
prod['url'] = getText(product.getElementsByTagName('DetailPageURL')[0].childNodes)
prod['title'] = getText(product.getElementsByTagName('Title')[0].childNodes)
prod['img'] = image
prod['price'] = price
#imagesets = getText(product.getElementsByTagName('MediumImage'))[0].childNodes
#print imagesets
#imageset = getText(imagesets.getElementsByTagName('ImageSet'))[0]
data += [prod]
return data
def amazon_search():
api = API(AWS_KEY, SECRET_KEY, 'us', ASSOC_TAG)
result = api.item_search('All',
ResponseGroup='Large', AssociateTag='boitba-20', Keywords='tent marmot', ItemPage=2)
total_results = result.results
#item_search returns pages not items
# extract paging information
#total_results = result.results
#Stotal_pages = len(result) # or result.pages
#~ from lxml import etree
#~ print etree.tostring(root, pretty_print=True)
return render_template("amazon_search.html", node = result, total_results=total_results)
def amazon_search():
api = API(AWS_KEY, SECRET_KEY, 'us', ASSOC_TAG)
result = api.item_search('All',
ResponseGroup='Large',
AssociateTag='boitba-20',
Keywords='tent marmot',
ItemPage=2)
total_results = result.results
#item_search returns pages not items
# extract paging information
#total_results = result.results
#Stotal_pages = len(result) # or result.pages
#~ from lxml import etree
#~ print etree.tostring(root, pretty_print=True)
return render_template("amazon_search.html",
node=result,
total_results=total_results)
class AmazonProductSearch():
def __init__(self, aws_access_key, aws_secret_key, affiliate_key):
self.api = API(aws_access_key, aws_secret_key, 'us', affiliate_key)
def _create_product(self, result):
product = {}
product['ASIN'] = str(result.ASIN)
product['Amount'] = str(result.OfferSummary.LowestNewPrice.Amount)
product['Binding'] = str(result.ItemAttributes.Binding)
product['DetailPageURL'] = str(result.DetailPageURL)
return product
def item_search(self, title, actor, expected_running_time,
ResponseGroup='OfferFull, Medium', release_year=None):
'''
This method searches Amazon for DVD, Blu-ray, and/or Amazon Instant
Video listings of the movie that we are searching. Actor and running
time are included in the query to improve the accuracy of the results
returned by Amazon.
Args:
title: Title of the movie
actor: Top billing actor for the movie
expected_running_time: Total running time for the movie
ResponseGroup: See response group in amazon product search api
documentation
'''
try:
results = self.api.item_search('DVD', actor=actor, Keywords=title,
ResponseGroup=ResponseGroup)
except Exception as e:
print e
return []
rv = []
max_release_year_diff = 1
max_running_time_diff = 5
bindings_seen = {"DVD": False, "Blu-ray": False,
"Amazon Instant Video": False}
for result in results:
etree.tostring(result, pretty_print=True)
try:
if all(bindings_seen.values()):
return rv
result_binding = str(result.ItemAttributes.Binding)
result_release_year = int(str(result.ItemAttributes.ReleaseDate).split('-')[0])
result_running_time = int(result.ItemAttributes.RunningTime)
result_title = str(result.ItemAttributes.Title)
if fuzz.partial_ratio(title.lower(), result_title.lower()) < 100:
continue
if release_year is not None and abs(release_year - result_release_year) > max_release_year_diff:
continue
if abs(expected_running_time - result_running_time) > max_running_time_diff:
continue
if result_binding not in bindings_seen.keys():
continue
if bindings_seen.get(result_binding):
continue
rv.append(self._create_product(result))
bindings_seen[result_binding] = True
except Exception as e:
print e
continue
return rv
# -*- coding: utf-8 -*-
from amazonproduct.api import API
from amazonproduct.errors import AWSError
from amazonproduct.processors import BaseProcessor
import BeautifulSoup
class SoupProcessor(BaseProcessor):
def parse(self, fp):
soup = BeautifulSoup.BeautifulStoneSoup(fp.read())
for error in soup.findAll('error'):
code = error.find('code').text
msg = error.find('message').text
raise AWSError(code, msg)
return soup
if __name__ == '__main__':
api = API(locale='jp', processor=SoupProcessor())
result = api.item_search('Apparel', Condition='All', Availability='Available', Keywords='Shirt')
print result
"""
Get all books published by "Galileo Press".
"""
from amazonproduct.api import API
import lxml
if __name__ == '__main__':
# Don't forget to create file ~/.amazon-product-api
# with your credentials (see docs for details)
api = API(locale='de')
result = api.item_search('Books',
Publisher='Galileo Press',
ResponseGroup='Large')
# extract paging information
total_results = result.results
total_pages = len(result) # or result.pages
for book in result:
print 'page %d of %d' % (result.current, total_pages)
#~ from lxml import etree
#~ print etree.tostring(book, pretty_print=True)
print book.ASIN,
print unicode(book.ItemAttributes.Author), ':',
print unicode(book.ItemAttributes.Title),
'Brand', 'Manufacturer', 'Model', 'OperatingSystem', 'ProductGroup',
'ProductTypeName', 'ReleaseDate', 'Title'
]
item_img = ['SmallImage', 'MediumImage', 'LargeImage']
item_offer = ['SalesRank', 'TotalNew']
item_price = [
'LowestNewPrice', 'LowestRefurbishedPrice', 'LowestUsedPrice'
]
img_attr = ['Height', 'URL', 'Width']
connection = Connection()
db = connection.linux_laptops
api = API(AWS_KEY, SECRET_KEY, 'us', associate_tag='notebux-20')
paginator = api.item_search('Electronics',
Keywords='linux laptop',
ResponseGroup='Medium')
for root in paginator:
nspace = root.nsmap.get(None, '')
items = root.xpath('//aws:Items/aws:Item', namespaces={'aws': nspace})
for i in items:
doc = {}
try:
doc['ASIN'] = str(i.ASIN)
doc['URL'] = str(i.DetailPageURL)
# Images
doc['Images'] = {}
for a in item_img:
from amazonproduct.api import API
from config import AWS_KEY, SECRET_KEY
if __name__ == '__main__':
item_attr = ['Brand', 'Manufacturer', 'Model', 'OperatingSystem', 'ProductGroup', 'ProductTypeName', 'ReleaseDate', 'Title']
item_img = ['SmallImage', 'MediumImage', 'LargeImage']
item_offer = ['SalesRank', 'TotalNew']
item_price = ['LowestNewPrice', 'LowestRefurbishedPrice', 'LowestUsedPrice']
img_attr = ['Height', 'URL', 'Width']
connection = Connection()
db = connection.linux_laptops
api = API(AWS_KEY, SECRET_KEY, 'us', associate_tag='notebux-20')
paginator = api.item_search('Electronics', Keywords='linux laptop', ResponseGroup='Medium')
for root in paginator:
nspace = root.nsmap.get(None, '')
items = root.xpath('//aws:Items/aws:Item', namespaces={'aws' : nspace})
for i in items:
doc = {}
try:
doc['ASIN'] = str(i.ASIN)
doc['URL'] = str(i.DetailPageURL)
# Images
doc['Images'] = {}
for a in item_img:
if hasattr(i, a):
"""
Get all books published by "Galileo Press".
"""
from amazonproduct.api import API
import lxml
if __name__ == '__main__':
# Don't forget to create file ~/.amazon-product-api
# with your credentials (see docs for details)
api = API(locale='de')
result = api.item_search('Books', Publisher='Galileo Press',
ResponseGroup='Large')
# extract paging information
total_results = result.results
total_pages = len(result) # or result.pages
for book in result:
print 'page %d of %d' % (result.current, total_pages)
#~ from lxml import etree
#~ print etree.tostring(book, pretty_print=True)
print book.ASIN,
print unicode(book.ItemAttributes.Author), ':',
print unicode(book.ItemAttributes.Title),
