def find_entry(self, path, match):
"""Looks for a particular entry in the etree.
Returns the element looked for/None.
"""
xp = path.xpath(self.xpath)
f = filter(lambda x: x.text == match, xp)
return f[0].text if len(f) else None
def get_all_entry(self, path):
"""All entries in the etree is converted to the dictionary
Returns the list of dictionary/didctionary.
"""
xps = path.xpath(self.xpath)
if type(xps) is not list:
return self._get_one(xps)
val = []
for xp in xps:
val.append(self._get_one(xp))
return val
def book_pare(self, response):
item = BookSiteMainItem()
for path in response.xpath(
'//*[@id="content_inner"]/article/div[1]/div[2]'):
item['full_bookname'] = path.xpath(
'//*[@id="content_inner"]/article/div[1]/div[2]/h1/text()'
).get()
item['priceinpounds'] = path.xpath(
'//*[@id="content_inner"]/article/div[1]/div[2]/p[1]/text()'
).get()
item['rating'] = path.xpath(
'//*[@id="content_inner"]/article/div[1]/div[2]/p[3]/@class'
).get()
item['upc'] = path.xpath(
'//*[@id="content_inner"]/article/table[@class="table table-striped"]//tr/td'
)[0].get().split()[0]
item['producttype'] = path.xpath(
'//*[@id="content_inner"]/article/table[@class="table table-striped"]//tr/td'
)[1].get().split()[0]
item['priceexcludetax'] = path.xpath(
'//*[@id="content_inner"]/article/table[@class="table table-striped"]//tr/td'
)[2].get().split()[0]
item['priceincludetax'] = path.xpath(
'//*[@id="content_inner"]/article/table[@class="table table-striped"]//tr/td'
)[3].get().split()[0]
item['tax'] = path.xpath(
'//*[@id="content_inner"]/article/table[@class="table table-striped"]//tr/td'
)[4].get().split()[0]
item['availability'] = path.xpath(
'//*[@id="content_inner"]/article/table[@class="table table-striped"]//tr/td'
)[5].get().split()[0:2]
item['numberavailable'] = path.xpath(
'//*[@id="content_inner"]/article/table[@class="table table-striped"]//tr/td'
)[5].get().split()[2:]
item['numberofreviews'] = path.xpath(
'//*[@id="content_inner"]/article/table[@class="table table-striped"]//tr/td'
)[6].get().split()[0]
yield item
