def parse(self, response):
loader = ContentLoader(response=response)
loader.add_css('content', 'div#cceb7e72db-b12d-4887-8946-387a18f7f068')
loader.add_css(
'title',
'div#cceb7e72db-b12d-4887-8946-387a18f7f068 h1.headline span span::text'
)
return loader.load_item()
def parse(self, response):
loader = ContentLoader(response=response)
loader.add_xpath('content',
'//table[@class="content"]/tr[1]/td[@class="col2"]')
loader.add_xpath(
'title',
'//table[@class="content"]/tr[1]/td[@class="col2"]//font[1]/text()'
)
return loader.load_item()
def parse(self, response):
# The ContentLoader line always stays the same.
loader = ContentLoader(response=response)
# We need to scrape content and title.
# Supply CSS selectors corresponding to content and title on the page(s).
loader.add_css('content', 'div#bigContentContainer')
loader.add_css('title', 'div#bigContentContainer h1')
# The loader.load_itemm() line always stays the same.
return loader.load_item()
def parse_post(self, response):
loader = ContentLoader(response=response)
loader.add_css('title', 'div.heading h2::text')
loader.add_css('content', 'div.article')
return loader.load_item()
def parse_post(self, response):
loader = ContentLoader(response=response)
loader.add_xpath('content', '//table[2]')
loader.add_css('title', 'span.contTitle2')
return loader.load_item()
def parse_post(self, response):
loader = ContentLoader(response=response)
loader.add_css('content', 'div.grve-main-content-wrapper')
page_loader = loader.nested_css('div.grve-main-content-wrapper')
page_loader.add_css('title', 'h1, h2, h3, h4')
return loader.load_item()
def parse(self, response):
loader = ContentLoader(response=response)
loader.add_css('title', 'article header h2::text')
loader.add_css('content', 'article div.mura-region-local')
return loader.load_item()
def parse(self, response):
loader = ContentLoader(response=response)
loader.add_css('content', 'div#scc-portal-article-content-container')
loader.add_css('title', 'div#scc-portal-article-content-container h1')
return loader.load_item()
def parse(self, response):
loader = ContentLoader(response=response)
loader.add_css('content', 'main#PAGES_CONTAINER')
loader.add_css('title', 'title::text')
return loader.load_item()
def parse(self, response):
loader = ContentLoader(response=response)
loader.add_css('content', 'main.page-content')
loader.add_css('title', 'main.page-content h1')
return loader.load_item()
def parse_post(self, response):
loader = ContentLoader(response=response)
loader.add_css('content', 'div.content')
loader.add_css('title', 'div.item h3::text')
return loader.load_item()
def parse(self, response):
loader = ContentLoader(response=response)
# 'div#main-body' is for sfdph.org, 'article' is for sfcdcp.org.
loader.add_css('content', 'div#main-body, article')
loader.add_css('title', 'h1')
return loader.load_item()
def parse_post(self, response):
loader = ContentLoader(response=response)
loader.add_css('content', 'article')
loader.add_css('title', 'h1')
return loader.load_item()
def parse_post(self, response):
loader = ContentLoader(response=response)
loader.add_css('content', 'div.vpadcontentdiv')
loader.add_css('title', 'div#newsdetails h2::text')
return loader.load_item()
def parse(self, response):
loader = ContentLoader(response=response)
loader.add_value('title', 'Sacramento Public Health')
loader.add_css('content', 'div.news')
return loader.load_item()
def parse_post(self, response):
loader = ContentLoader(response=response)
loader.add_css('content', 'article#content_begins')
loader.add_css('title', 'article#content_begins h2::text')
return loader.load_item()
def parse(self, response):
loader = ContentLoader(response=response)
loader.add_css('title', 'div.content h3')
loader.add_css('content', 'div.content')
return loader.load_item()
def parse(self, response):
loader = ContentLoader(response=response)
loader.add_css('content', 'div#main')
loader.add_css('title', 'h1#page-title')
return loader.load_item()