def extract_links(self, response):
xs = HtmlXPathSelector(response)
base_url = xs.select('//base/@href').extract()
base_url = urljoin_rfc(response.url,
base_url[0]) if base_url else response.url
links = []
for location in self.locations:
if isinstance(location, basestring):
selectors = xs.select(location)
elif isinstance(location, (XPathSelectorList, HtmlXPathSelector)):
selectors = [location] if isinstance(
location, HtmlXPathSelector) else location
else:
continue
for selector in selectors:
links.extend(
self.extract_from_selector(selector, response.encoding))
seen, ret = set(), []
for link in links:
link.url = urljoin_rfc(base_url, link.url, response.encoding)
if self.unique:
if link.url in seen:
continue
else:
seen.add(link.url)
if self.canonicalize:
link.url = canonicalize_url(link.url)
ret.append(link)
return ret
def test_null_bytes(self):
hxs = HtmlXPathSelector(text='<root>la\x00la</root>')
self.assertEqual(hxs.extract(),
u'<html><body><root>lala</root></body></html>')
xxs = XmlXPathSelector(text='<root>la\x00la</root>')
self.assertEqual(xxs.extract(), u'<root>lala</root>')
def extract_links(self, response):
xs = HtmlXPathSelector(response)
base_url = xs.select('//base/@href').extract()
base_url = urljoin_rfc(response.url, base_url[0]) if base_url else response.url
links = []
for location in self.locations:
if isinstance(location, basestring):
selectors = xs.select(location)
elif isinstance(location, (XPathSelectorList, HtmlXPathSelector)):
selectors = [location] if isinstance(location, HtmlXPathSelector) else location
else:
continue
for selector in selectors:
links.extend(self.extract_from_selector(selector, response.encoding))
seen, ret = set(), []
for link in links:
link.url = urljoin_rfc(base_url, link.url, response.encoding)
if self.unique:
if link.url in seen:
continue
else:
seen.add(link.url)
if self.canonicalize:
link.url = canonicalize_url(link.url)
ret.append(link)
return ret
def test_null_bytes(self):
hxs = HtmlXPathSelector(text='<root>la\x00la</root>')
self.assertEqual(hxs.extract(),
u'<html><body><root>lala</root></body></html>')
xxs = XmlXPathSelector(text='<root>la\x00la</root>')
self.assertEqual(xxs.extract(),
u'<root>lala</root>')
def parse_item(self, response):
hxs = HtmlXPathSelector(response)
# Assign given elements
article = ArticleItem()
article['source'] = self.source
article['url'] = response.url
# Parse Category
try:
category_str = sanitize(self.get_category(response))
article['category'] = capitalizeFirstCharInWord(
self.normalize_category(self.parse_category(category_str)))
except:
article['category'] = ''
# Parse Title
try:
article['title'] = sanitize(
hxs.select(self.xpath_title).extract()[0])
except:
article['title'] = ''
# Parse Content
paragraphs = hxs.select(self.xpath_content).extract()
lines = []
for paragraph in paragraphs:
line = sanitize(paragraph)
if len(line) > 0:
lines.append(line)
article['content'] = '\n'.join(lines)
# Parse Subtitle
try:
article['subtitle'] = capitalizeFirstCharInWord(
sanitize(hxs.select(self.xpath_subtitle).extract()[0]))
except:
article['subtitle'] = ''
# Parse Published_at
try:
date_str = sanitize(
hxs.select(self.xpath_published_at).extract()[0])
article['published_at'] = self.parse_date(date_str)
except:
article['published_at'] = ''
# Parse Place
try:
place_str = sanitize(hxs.select(self.xpath_place).extract()[0])
article['place'] = capitalizeFirstCharInWord(
self.parse_place(place_str))
except:
article['place'] = ''
# Parse Author
try:
author_str = sanitize(hxs.select(self.xpath_author).extract()[0])
article['author'] = capitalizeFirstCharInWord(
self.parse_author(author_str))
except:
article['author'] = ''
# Debug
if self.debug == True:
print article
print ''
else:
return article
def get_category(self, response):
hxs = HtmlXPathSelector(response)
return hxs.select(self.xpath_category).extract()[0]
def parse_item(self, response):
hxs = HtmlXPathSelector(response)
# Assign given elements
article = ArticleItem()
article['source'] = self.source
article['url'] = response.url
# Parse Category
try:
category_str = sanitize(self.get_category(response))
article['category'] = capitalizeFirstCharInWord(self.normalize_category(self.parse_category(category_str)))
except:
article['category'] = ''
# Parse Title
try:
article['title'] = sanitize(hxs.select(self.xpath_title).extract()[0])
except:
article['title'] = ''
# Parse Content
paragraphs = hxs.select(self.xpath_content).extract()
lines = []
for paragraph in paragraphs:
line = sanitize(paragraph)
if len(line) > 0:
lines.append(line)
article['content'] = '\n'.join(lines)
# Parse Subtitle
try:
article['subtitle'] = capitalizeFirstCharInWord(sanitize(hxs.select(self.xpath_subtitle).extract()[0]))
except:
article['subtitle'] = ''
# Parse Published_at
try:
date_str = sanitize(hxs.select(self.xpath_published_at).extract()[0])
article['published_at'] = self.parse_date(date_str)
except:
article['published_at'] = ''
# Parse Place
try:
place_str = sanitize(hxs.select(self.xpath_place).extract()[0])
article['place'] = capitalizeFirstCharInWord(self.parse_place(place_str))
except:
article['place'] = ''
# Parse Author
try:
author_str = sanitize(hxs.select(self.xpath_author).extract()[0])
article['author'] = capitalizeFirstCharInWord(self.parse_author(author_str))
except:
article['author'] = ''
# Debug
if self.debug == True:
print article
print ''
else:
return article
def get_category(self, response):
hxs = HtmlXPathSelector(response)
return hxs.select(self.xpath_category).extract()[0]
