class ArtsciBiologyGooseSpider(CrawlSpider):
name = "artsci_biology_goose"
allowed_domains = ["concordia.ca"]
start_urls = [
'http://www.concordia.ca/artsci/biology.html',
]
rules = (
Rule(LinkExtractor(allow=allowed_links(start_urls[0])), callback='parse_item', follow=True),
)
def parse_item(self, response):
article = Goose().extract(raw_html=response.body)
yield Article(title=article.title,
text=article.cleaned_text,
url=response.url,
field=self.name)
class ArtsciMysterySpider(CrawlSpider):
name = "artsci_mystery"
allowed_domains = ["concordia.ca"]
start_urls = [
'https://www.concordia.ca/artsci/science-college/about/life-at-the-college.html',
]
rules = (
Rule(LinkExtractor(allow=allowed_links(start_urls[0])), callback='parse_item', follow=True),
)
def parse_item(self, response):
title = response.css('title::text').extract_first()
extractor = Extractor(extractor='ArticleExtractor', html=response.body)
yield Article(title=title,
text=extractor.getText(),
url=response.url,
field=self.name)
class ArtsciGeographySpider(CrawlSpider):
name = "artsci_geography"
allowed_domains = ["concordia.ca"]
start_urls = [
'http://www.concordia.ca/artsci/geography-planning-environment.html',
]
rules = (
Rule(LinkExtractor(allow=allowed_links(start_urls[0])), callback='parse_item', follow=True),
)
def parse_item(self, response):
title = response.css('title::text').extract_first()
extractor = Extractor(extractor='ArticleExtractor', html=response.body)
yield Article(title=title,
text=extractor.getText(),
url=response.url,
field=self.name)
class ArtsciBiologyXpathSpider(CrawlSpider):
name = "artsci_biology_xpath"
allowed_domains = ["concordia.ca"]
start_urls = [
'http://www.concordia.ca/artsci/biology.html',
]
rules = (
Rule(LinkExtractor(allow=allowed_links(start_urls[0])), callback='parse_item', follow=True),
)
def parse_item(self, response):
title = response.css('title::text').extract_first()
body = parse_body(response)
yield Article(title=title,
text=body,
url=response.url,
field=self.name)
