def parse_article(self, response):
text = ' '.join([x.strip() for x in response.css('div.article-body *::text').extract() if x])
author = ' '.join([x.strip() for x in response.css('p.byline *::text').extract() if x])
yield Article(
title = response.meta.get('title', ''),
url = response.meta.get('url', ''),
published = response.meta.get('date', datetime.now()),
content = text,
author = author,
source = 'San Francisco Chronicle'
)
def parse_article(self, response):
text = ' '.join([
x.strip() for x in response.css(
'div.pb-f-article-body div[data-type=text] *::text').extract()
if x
])
author = ' '.join([
x.strip() for x in response.css('span.byline *::text').extract()
if x
])
yield Article(title=response.meta.get('title', ''),
url=response.meta.get('url', ''),
published=response.meta.get('date', datetime.now()),
content=text,
author=author,
source='LA Times')
def parse_article(self, response):
selector = '.pb-f-article-body'
text = ' '.join([
x.strip() for x in response.css(
'div[itemprop=articleBody] *::text').extract() if x
])
author = ' '.join([
x.strip() for x in response.css('div.trb_ar_by *::text').extract()
if x
])
yield Article(title=response.meta.get('title', ''),
url=response.meta.get('url', ''),
published=response.meta.get('date', datetime.now()),
content=text,
author=author,
source='San Diego Union Tribune')
def parse_article(self, response):
selector = '.pb-f-article-body'
text = ' '.join([
x.strip()
for x in response.css('div#content-body *::text').extract() if x
])
author = ' '.join([
x.strip() for x in response.css('div.byline *::text').extract()
if x
])
yield Article(title=response.meta.get('title', ''),
url=response.meta.get('url', ''),
published=response.meta.get('date', datetime.now()),
content=text,
author=author,
source='Sacramento Bee')