def authors(self):
"""Returns the authors names, co-writers or manufacturers for every item.
>>> authors = wishlist.authors()
"""
ret = []
attr = ('de ', 'di ', 'by ', 'von ')
for author in self.page.xpath("//div[@class='pTitle']"):
subtree = helpers.tostring(author,
encoding='unicode',
method='html',
pretty_print=True)
if 'span' in subtree:
parser = helpers.etree.HTMLParser()
div = helpers.etree.fromstring(subtree, parser)
res = div.xpath("//span[@class='small itemByline']//text()")
for author in res:
author = author.replace('~', '').strip()
if author.startswith(tuple(attr)):
author = author[3:].strip()
ret.append(helpers._stripper(author))
else:
ret.append(helpers._stripper(author))
else:
ret.append(ur'')
dirt = ['DVD', 'VHS']
for item in dirt:
while item in ret:
ret.remove(item)
return ret
def wishlists_details(self):
"""
Returns a tuple with lists, the first with all wishlists
codes and the second with their total number of items
(i.e. wishlist size).
>>> details = person.wishlists_details()
"""
retcodes = []
for code in self.page.xpath("//div[@id='profile']/div[@id='regListpublicBlock']/div/@id"):
retcodes.append(helpers._stripper(code.replace('regListsList', '')))
retsizes = []
for size in self.page.xpath("//div[@id='profile']/div[@id='regListpublicBlock']/div/div/span[1]//text()"):
retsizes.append(helpers._stripper(size))
return retcodes, retsizes
def basic_info(self):
"""
Returns the name of the wishlist owner and, if available,
the address of its profile picture.
>>> info = person.basic_info()
"""
# wishlists are supposed to show a first name, so it's safe to assume it will never be null
ret = []
for name in self.page.xpath("//td[@id='profile-name-Field']//text()"):
ret.append(helpers._stripper(name))
photo = self.page.xpath("//div[@id='profile']/div/img/@src")
if photo:
filename = photo[0].split('.')
filename = '.'.join(filename[:-2]) + '.' + filename[-1]
ret.append(helpers._stripper(filename))
return ret
def titles(self):
"""
Returns items titles, even if they are pretty long
ones (like academic books or journals).
>>> titles = wishlist.titles()
"""
ret = []
for title in self.page.xpath("//div[@class='pTitle']/strong//text()"):
ret.append(helpers._stripper(title))
return ret
def covers(self):
"""Returns the addresses of items pictures (e.g. book covers, albums pictures).
>>> covers = wishlist.covers()
"""
ret = []
for filename in self.page.xpath(
"//div/form/table/tbody[*]/tr[*]/td[*]/div[@class='pImage']/img/@src"
):
filename = filename.split('.')
filename = '.'.join(filename[:-2]) + '.' + filename[-1]
ret.append(helpers._stripper(filename))
return ret
def via(self):
"""
Returns the sorted original web pages from which the wished item was
pulled, only for Universal items not sold by Amazon directly.
>>> via = wishlist.via()
"""
ret = []
for url in self.page.xpath(
"//div/form/table/tbody[*]/tr[*]/td[*]/strong[2]//text()"):
ret.append(helpers._stripper(url))
ret = sorted(list(set(ret)))
return ret
def ideas(self):
"""Returns a list of ideas to shop for later, as reminders
>>> ideas = wishlist.ideas()
"""
ret = []
ideas = [
ur'Idea', ur'Idee', ur'Id\xc3\xa9e', ur'\xe8\xa7\x82\xe5\xbf\xb5',
ur'Id\xc3\xa9ia'
]
for row in zip(self.titles(), self.prices()):
if row[1] in ideas:
ret.append(helpers._stripper(row[0]))
return ret
def list(self):
"""
Returns a list with tuples containing all matching usernames
and their main wishlist ID, with which you can get secondary
lists via the Wishlist() class.
>>> wishlists = search.list()
>>> for row in wishlists:
>>> print row
"""
# before pipe, page with usernames; after, single exact matches
wishlists = self.page.xpath(
"//td/span/a//@href | //div[@id='sortbarDisplay']/form//@action")
names = self.page.xpath(
"//td/span/a//text() | //h1[@class='visitor']//text()")
names = [helpers._stripper(n) for n in names]
codes = []
for code in wishlists:
codes.append(helpers._stripper(code.split('/')[3]))
# FIXME: hack not to return empty search results,
# whose only anchor text is not english
if not 'tg' in codes:
return zip(names, codes)
def urls(self):
"""Returns the page address of a given item in the wishlist, with its full details.
>>> urls = wishlist.urls()
"""
ret = []
for url in self.page.xpath("//tbody[@class='itemWrapper']//@name"):
if 'item' in url:
code = url.split('.')[3]
if code:
res = 'http://www.amazon' + self.domain + '/dp/' + code
else:
res = ''
ret.append(helpers._stripper(res))
return ret
def prices(self):
"""Returns the price tags for every item in a wishlist.
>>> prices = wishlist.prices()
"""
prices = self.page.xpath(
"//td[@class='pPrice'][not(text()) and not(strong)] | //td[@class='pPrice']/strong[3] | //td[@class='pPrice']/strong[1] | //td[@class='Price']/span/strong//text()"
)
# cleanups, every store has different price tag extras
if 'EUR' in self.currency:
dust = 'EUR'
elif 'CDN' in self.currency:
dust = 'CDN%s' % self.symbol
elif 'INR' in self.currency:
dust = 'Rs. '
elif 'CNY' in self.currency:
dust = u'\xa5'
elif 'BRL' in self.currency:
dust = 'R%s ' % self.symbol
elif 'JPY' in self.currency:
dust = u'\x81\x8f'
else:
dust = self.symbol
ret = []
for price in prices:
res = helpers.tostring(price,
encoding='unicode',
method='text',
pretty_print=True).strip()
if 'At' not in res:
# TODO: how would it work out for non-english stores? quite a huge bug ahead...
if 'Click' in res:
res = ''
if 'EUR' in self.currency or 'BRL' in self.currency:
res = res.replace(dust, '')
res = res.replace('.', '')
res = res.replace(',', '.')
else:
res = res.replace(dust, '')
res = res.replace(',', '')
ret.append(helpers._stripper(res))
return ret
