def supplemental_text(self):
# get all the known text blobs
# remove any found in editorial reviews
result = []
# kindle
# http://www.amazon.com/dp/1593080050
tag = self.soup.find('div', id='postBodyPS')
if tag:
text = strip_html_tags(unicode(tag))
if text:
result.append(text)
# paperbacks
# http://www.amazon.com/dp/1568822812
tag = self.soup.find('div', id='bookDescription_feature_div')
if tag:
tag = tag.find('div', class_=None)
text = strip_html_tags(unicode(tag))
if text:
result.append(text)
# extract from the javascript code that updates the iframe
# http://www.amazon.com/dp/1491268727
tag = self.soup.find('script', text=re.compile(ur'bookDescEncodedData', flags=re.I))
def supplemental_text(self):
# get all the known text blobs
# remove any found in editorial reviews
result = []
# kindle
# http://www.amazon.com/dp/1593080050
tag = self.soup.find('div', id='postBodyPS')
if tag:
text = strip_html_tags(unicode(tag))
if text:
result.append(text)
# paperbacks
# http://www.amazon.com/dp/1568822812
tag = self.soup.find('div', id='bookDescription_feature_div')
if tag:
tag = tag.find('div', class_=None)
text = strip_html_tags(unicode(tag))
if text:
result.append(text)
# extract from the javascript code that updates the iframe
# http://www.amazon.com/dp/1491268727
tag = self.soup.find('script',
text=re.compile(ur'bookDescEncodedData',
flags=re.I))
def author_bio(self):
tag = self.soup.find('div', class_='mainContent')
if tag:
text = strip_html_tags(unicode(tag))
if text:
return text
return None
def total_reviews(self):
tag = self.soup.find('span', class_='totalReviewCount')
if tag:
text = strip_html_tags(unicode(tag))
if text:
return text
return None
def author_bio(self):
tag = self.soup.find('div', class_='mainContent')
if tag:
text = strip_html_tags(unicode(tag))
if text:
return text
return None
text = strip_html_tags(unicode(tag))
if text:
result.append(text)
# extract from the javascript code that updates the iframe
# http://www.amazon.com/dp/1491268727
tag = self.soup.find('script',
text=re.compile(ur'bookDescEncodedData',
flags=re.I))
if tag:
match = re.search(
ur'bookDescEncodedData\s=\s"(?P<description>[^",]+)', tag.text)
if match:
text = match.group('description')
text = urllib.unquote(text)
text = strip_html_tags(text)
if text:
result.append(text)
# http://www.amazon.com/dp/1616611359
for tag in self.soup.find_all('div',
class_='productDescriptionWrapper'):
text = unicode(tag)
text = strip_html_tags(text)
if text:
result.append(text)
# android apps
# http://www.amazon.com/dp/B008A1I0SU
tag = self.soup.find('div', class_='mas-product-description-wrapper')
if tag:
def text(self):
tag = self.soup.find('span', class_='description')
return strip_html_tags(unicode(tag))
def supplemental_text(self):
# get all the known text blobs
# remove any found in editorial reviews
result = []
# kindle
# http://www.amazon.com/dp/1593080050
tag = self.soup.find('div', id='postBodyPS')
if tag:
text = strip_html_tags(unicode(tag))
if text:
result.append(text)
# paperbacks
# http://www.amazon.com/dp/1568822812
tag = self.soup.find('div', id='bookDescription_feature_div')
if tag:
tag = tag.find('div', class_=None)
text = strip_html_tags(unicode(tag))
if text:
result.append(text)
# extract from the javascript code that updates the iframe
# http://www.amazon.com/dp/1491268727
tag = self.soup.find('script',
text=re.compile(r'bookDescEncodedData',
flags=re.I))
if tag:
match = re.search(
r'bookDescEncodedData\s=\s"(?P<description>[^",]+)', tag.text)
if match:
text = match.group('description')
text = urllib.unquote(text)
text = strip_html_tags(text)
if text:
result.append(text)
# http://www.amazon.com/dp/1616611359
for tag in self.soup.find_all('div',
class_='productDescriptionWrapper'):
text = unicode(tag)
text = strip_html_tags(text)
if text:
result.append(text)
# android apps
# http://www.amazon.com/dp/B008A1I0SU
tag = self.soup.find('div', class_='mas-product-description-wrapper')
if tag:
sub_tag = tag.find('div', class_='content')
if sub_tag:
tag = sub_tag
text = strip_html_tags(unicode(tag))
if text:
result.append(text)
# amazon instant video
# http://www.amazon.com/dp/B004C0YS5C
# older method
tag = self.soup.find('div', class_='prod-synopsis')
if tag:
text = strip_html_tags(unicode(tag))
if text:
result.append(text)
# newer method
tag = self.soup.find('div', class_='dv-simple-synopsis')
if tag:
text = strip_html_tags(unicode(tag))
if text:
result.append(text)
# http://www.amazon.com/dp/B0006FUAD6
tag = self.soup.find('div',
id=re.compile('feature-bullets', flags=re.I))
if tag:
tags = map(unicode, tag.find_all('span'))
text = strip_html_tags(u''.join(tags))
if text:
result.append(text)
# http://www.amazon.com/dp/B00DHF39KS
tag = self.soup.find('div', class_='aplus')
if tag:
text = strip_html_tags(unicode(tag))
if text:
result.append(text)
return result
tag = self.soup.find('div', id='bookDescription_feature_div')
if tag:
tag = tag.find('div', class_=None)
text = strip_html_tags(unicode(tag))
if text:
result.append(text)
# extract from the javascript code that updates the iframe
# http://www.amazon.com/dp/1491268727
tag = self.soup.find('script', text=re.compile(ur'bookDescEncodedData', flags=re.I))
if tag:
match = re.search(ur'bookDescEncodedData\s=\s"(?P<description>[^",]+)', tag.text)
if match:
text = match.group('description')
text = urllib.unquote(text)
text = strip_html_tags(text)
if text:
result.append(text)
# http://www.amazon.com/dp/1616611359
for tag in self.soup.find_all('div', class_='productDescriptionWrapper'):
text = unicode(tag)
text = strip_html_tags(text)
if text:
result.append(text)
# android apps
# http://www.amazon.com/dp/B008A1I0SU
tag = self.soup.find('div', class_='mas-product-description-wrapper')
if tag:
sub_tag = tag.find('div', class_='content')
def supplemental_text(self):
# get all the known text blobs
# remove any found in editorial reviews
result = []
# kindle
# http://www.amazon.com/dp/1593080050
tag = self.soup.find("div", id="postBodyPS")
if tag:
text = strip_html_tags(unicode(tag))
if text:
result.append(text)
# paperbacks
# http://www.amazon.com/dp/1568822812
tag = self.soup.find("div", id="bookDescription_feature_div")
if tag:
tag = tag.find("div", class_=None)
text = strip_html_tags(unicode(tag))
if text:
result.append(text)
# extract from the javascript code that updates the iframe
# http://www.amazon.com/dp/1491268727
tag = self.soup.find("script", text=re.compile(r"bookDescEncodedData", flags=re.I))
if tag:
match = re.search(r'bookDescEncodedData\s=\s"(?P<description>[^",]+)', tag.text)
if match:
text = match.group("description")
text = urllib.unquote(text)
text = strip_html_tags(text)
if text:
result.append(text)
# http://www.amazon.com/dp/1616611359
for tag in self.soup.find_all("div", class_="productDescriptionWrapper"):
text = unicode(tag)
text = strip_html_tags(text)
if text:
result.append(text)
# android apps
# http://www.amazon.com/dp/B008A1I0SU
tag = self.soup.find("div", class_="mas-product-description-wrapper")
if tag:
sub_tag = tag.find("div", class_="content")
if sub_tag:
tag = sub_tag
text = strip_html_tags(unicode(tag))
if text:
result.append(text)
# amazon instant video
# http://www.amazon.com/dp/B004C0YS5C
# older method
tag = self.soup.find("div", class_="prod-synopsis")
if tag:
text = strip_html_tags(unicode(tag))
if text:
result.append(text)
# newer method
tag = self.soup.find("div", class_="dv-simple-synopsis")
if tag:
text = strip_html_tags(unicode(tag))
if text:
result.append(text)
# http://www.amazon.com/dp/B0006FUAD6
tag = self.soup.find("div", id=re.compile("feature-bullets", flags=re.I))
if tag:
tags = map(unicode, tag.find_all("span"))
text = strip_html_tags(u"".join(tags))
if text:
result.append(text)
# http://www.amazon.com/dp/B00DHF39KS
tag = self.soup.find("div", class_="aplus")
if tag:
text = strip_html_tags(unicode(tag))
if text:
result.append(text)
return result
