def parse(self, response):
# iterate entries
for entry in response.css('div').css('li.archive-item-component'):
#retrieve info for our current post
item = ScrapyItem()
# p.post-excerpt class de type p = post-excerpt
item['source'] = 'wired'
temp_string = entry.css('time::text').extract_first()
item['brief'] = entry.css('a').css('p.archive-item-component__desc::text').extract_first()
item['url'] = entry.css('a::attr(href)').extract_first()
item['title'] = entry.css('a').css('h2::text').extract_first()
# check time
now = datetime.datetime.now()
now = now.strftime("%Y-%m-%dT%H:%M:%S.%f%z")
item['tstamp'] = now
# transfer time into ISO 8601
temp = timestring.Date(temp_string).date
item['date'] = temp.strftime("%Y-%m-%dT%H:%M:%S.%f%z")
# item['date'] = entry.css('time::text').extract_first()
# item['brief'] = entry.css('p.post-excerpt::text').extract_first()
# item['url'] = entry.css('h2').css('a::attr(href)').extract_first()
# item['title'] = entry.css('h2').css('a::text').extract_first()
yield item
def parse(self, response):
news = response.css('div.sr')
titles = news.css('h4')
briefs = news.css('p')
# iterate entries
for j in range(len(titles)):
#retrieve info for our current post
item = ScrapyItem()
item['source'] = 'esa'
temp_string = briefs[j].css('::text').extract_first()
if briefs[j].css('b::text').extract_first() != '...':
continue
item['brief'] = briefs[j].css('::text').extract()[1]
item['url'] = titles[j].css('a::attr(href)').extract_first()
item['title'] = titles[j].css('a::text').extract_first()
# check time
now = datetime.datetime.now()
now = now.strftime("%Y-%m-%dT%H:%M:%S.%f%z")
item['tstamp'] = now
# transfer time into ISO 8601
temp = timestring.Date(temp_string).date
item['date'] = temp.strftime("%Y-%m-%dT%H:%M:%S.%f%z")
yield item
def parse(self, response):
# iterate entries
for entry in response.css('div.listing-wide__inner'):
item = ScrapyItem()
#retrieve info for our current post
item['source'] = 'scientificamerican'
temp_string = entry.css('div.t_meta::text').extract_first().split(
' — ')[0]
item['brief'] = entry.css('p::text').extract_first()
item['url'] = entry.css('h2').css('a::attr(href)').extract_first()
item['title'] = entry.css('h2').css('a::text').extract_first()
# check time
now = datetime.datetime.now()
now = now.strftime("%Y-%m-%dT%H:%M:%S.%f%z")
item['tstamp'] = now
# transfer time into ISO 8601
temp = timestring.Date(temp_string).date
item['date'] = temp.strftime("%Y-%m-%dT%H:%M:%S.%f%z")
# request to article page
request = scrapy.Request(item['url'], callback=self.parse_article)
request.meta['item'] = item
yield request
paginate = response.css('div.pagination__right')
if paginate.css('a'):
next_link = 'https://www.scientificamerican.com/search/' + paginate.css(
'a::attr(href)').extract_first()
yield scrapy.Request(next_link)
def parse(self, response):
for entry in response.css('li.archive-item-component'):
item = ScrapyItem()
url_temp = entry.css('a::attr(href)').extract_first()
item['url'] = 'https://www.wired.com' + url_temp
item['source'] = 'wired'
temp_string = entry.css('time::text').extract_first()
item['brief'] = entry.css('a').css(
'p.archive-item-component__desc::text').extract_first()
item['title'] = entry.css('a').css('h2::text').extract_first()
# check time
now = datetime.datetime.now()
now = now.strftime("%Y-%m-%dT%H:%M:%S.%f%z")
item['tstamp'] = now
# transfer time into ISO 8601
temp = timestring.Date(temp_string).date
item['date'] = temp.strftime("%Y-%m-%dT%H:%M:%S.%f%z")
# request to article page
request = scrapy.Request(item['url'], callback=self.parse_article)
request.meta['item'] = item
yield request
# go to next page if exists
next_url = response.css('li.pagination-component__caret--right').css(
'a::attr(href)').extract_first()
if next_url:
yield scrapy.Request('https://www.wired.com' + next_url)
def parse(self, response):
#iterate entries
for entry in response.css('div.element2'):
#retrieve info for our current post
item = ScrapyItem()
item['source'] = 'NYTimes'
temp_string = entry.css('span.dateline::text').extract_first()
item['brief'] = entry.css('p.summary').extract_first()
item['url'] = entry.css('a::attr(href)').extract_first()
item['title'] = entry.css('a::text').extract_first()
# check time
now = datetime.datetime.now()
now = now.strftime("%Y-%m-%dT%H:%M:%S.%f%z")
item['tstamp'] = now
# transfer time into ISO 8601
temp = timestring.Date(temp_string).date
item['date'] = temp.strftime("%Y-%m-%dT%H:%M:%S.%f%z")
print(item)
yield item
def parse(self, response):
# iterate entries
for entry in response.css('li.wd_item'):
#retrieve info for our current post
item = ScrapyItem()
item['source'] = 'lockheed_martin'
temp_string = entry.css('div.wd_date::text').extract_first()
item['brief'] = entry.css('div').css('p::text').extract_first()
item['url'] = entry.css('a::attr(href)').extract_first()
item['title'] = entry.css('div').css('a::text').extract_first()
# check time
now = datetime.datetime.now()
now = now.strftime("%Y-%m-%dT%H:%M:%S.%f%z")
item['tstamp'] = now
# transfer time into ISO 8601
temp = timestring.Date(temp_string).date
item['date'] = temp.strftime("%Y-%m-%dT%H:%M:%S.%f%z")
# item['date'] = entry.css('time::text').extract_first()
# item['brief'] = entry.css('p.post-excerpt::text').extract_first()
# item['url'] = entry.css('h2').css('a::attr(href)').extract_first()
# item['title'] = entry.css('h2').css('a::text').extract_first()
yield item
def parse(self, response):
item = ScrapyItem()
i = 0
if NewsSpider.temp == False:
if NewsSpider.j == 0:
for entry in response.css('div').css(
'li.archive-item-component'):
np.put(NewsSpider.url_list, [i],
entry.css('a::attr(href)').extract_first())
#url_list = np.append(entry.css('a::attr(href)').extract_first())
url_temp = entry.css('a::attr(href)').extract_first()
item['source'] = 'wired'
temp_string = entry.css('time::text').extract_first()
item['brief'] = entry.css('a').css(
'p.archive-item-component__desc::text').extract_first(
)
item['url'] = entry.css('a::attr(href)').extract_first()
item['title'] = entry.css('a').css(
'h2::text').extract_first()
# check time
now = datetime.datetime.now()
now = now.strftime("%Y-%m-%dT%H:%M:%S.%f%z")
item['tstamp'] = now
# transfer time into ISO 8601
temp = timestring.Date(temp_string).date
item['date'] = temp.strftime("%Y-%m-%dT%H:%M:%S.%f%z")
i = i + 1
yield item
next_page = response.urljoin(NewsSpider.url_list.item(
NewsSpider.j))
NewsSpider.temp = True
NewsSpider.j = NewsSpider.j + 1
yield scrapy.Request(next_page, callback=self.parse)
else:
item['article'] = response.css('article').css('div').css(
'p::text').extract()
yield item
previous_page = 'https://www.wired.com/search/?page=1&q=rocket&size=1&sort=publishDate_tdt%20desc&types%5B0%5D=article'
NewsSpider.temp = False
yield scrapy.Request(previous_page, callback=self.parse)
def parse(self, response):
# iterate entries
for entry in response.css('div.newslist'):
#retrieve info for our current post
item = ScrapyItem()
item['source'] = 'roscosmos'
item['company'] = 'roscosmos'
temp_string = entry.css('div.date::text').extract_first()
item['brief'] = 'none'
item['url'] = entry.css('a::attr(href)').extract_first()
item['title'] = entry.css('div').css('a.name::text').extract_first()
# check time
now = datetime.datetime.now()
now = now.strftime("%Y-%m-%dT%H:%M:%S.%f%z")
item['tstamp'] = now
# transfer time into ISO 8601
temp = timestring.Date(temp_string).date
item['date'] = temp.strftime("%Y-%m-%dT%H:%M:%S.%f%z")
# request to article page
next_page = response.urljoin(item['url'])
if (temp.year<=2015):
request = scrapy.Request(next_page, callback=self.parse_article_before2015)
else:
request = scrapy.Request(next_page, callback=self.parse_article_after2015)
request.meta['item'] = item
yield request
if NewsSpider.temp == False:
NewsSpider.urls_list = response.css('div.text').css('a::attr(href)').extract()
NewsSpider.temp = True
for url in NewsSpider.urls_list:
next_search_page = response.urljoin(url)
if next_search_page:
yield scrapy.Request(next_search_page, callback=self.parse)
def parse(self, response):
# iterate entries
for entry in response.css('div.listing-wide__inner'):
#retrieve info for our current post
item = ScrapyItem()
item['source'] = 'scientificamerican'
item['date'] = entry.css('div.t_meta::text').extract_first().split(
' — ')[0]
item['brief'] = entry.css('p::text').extract_first()
item['url'] = entry.css('h2').css('a::attr(href)').extract_first()
item['title'] = entry.css('h2').css('a::text').extract_first()
# check time
now = datetime.datetime.now()
item['tstamp'] = now
yield item
def parse(self, response):
# iterate entries
if not response.css('li.wd_item'):
return
for entry in response.css('li.wd_item'):
# retrieve info for our current post
item = ScrapyItem()
item['source'] = 'lockheedmartin'
item['company'] = 'lockheedmartin'
# retrieve time string
temp_string = entry.css('div.wd_date::text').extract_first()
# transfer time into ISO 8601
temp = timestring.Date(temp_string).date
item['date'] = temp.strftime("%Y-%m-%dT%H:%M:%S.%f%z")
# retrieve abstract
item['brief'] = entry.css('div').css('p::text').extract_first()
# retrieve url
item['url'] = entry.css('a::attr(href)').extract_first()
# retrieve title
item['title'] = entry.css('div').css('a::text').extract_first()
# check time
now = datetime.datetime.now()
now = now.strftime("%Y-%m-%dT%H:%M:%S.%f%z")
item['tstamp'] = now
request = scrapy.Request(item['url'], self.parse_body)
request.meta['item'] = item
yield request
if len(response.css('li.wd_item')) == 1000:
# This website limits the articles shown articles to 1000; redo the request changing the 'end' date if the count reaches 1000
next_page = '&'.join(
self.start_urls[0].split('&')[:-1]) + '&end=' + item['date']
yield scrapy.Request(next_page)
def parse(self, response):
for entry in response.css('#archt').css('tr'):
# Declare the container item
item = ScrapyItem()
item['source'] = 'esa'
item['company'] = 'esa'
# Extract the date
tds = entry.css('td')
temp_string = tds[1].css('::text').extract_first()
temp_string += ' ' + tds[0].css('::text').extract_first()
temp_string += ' ' + tds[2].css('::text').extract_first()
# transfer time into ISO 8601
temp = timestring.Date(temp_string).date
item['date'] = temp.strftime("%Y-%m-%dT%H:%M:%S.%f%z")
# Extract the title
item['title'] = tds[3].css('a::text').extract_first()
# Extract the URL
item['url'] = 'http://www.esa.int' + tds[3].css(
'a::attr(href)').extract_first()
# Save current time
now = datetime.datetime.now()
now = now.strftime("%Y-%m-%dT%H:%M:%S.%f%z")
item['tstamp'] = now
# Proceed to retrieve the body and the abstract
request = scrapy.Request(item['url'],
callback=self.parse_body_brief)
request.meta['item'] = item
yield request
# Go to next page if possible
nextpage_url = response.css(
'a[title="Next Page"]::attr(href)').extract_first()
print('\n\n' + nextpage_url + '\n\n')
if nextpage_url:
yield scrapy.Request('http://www.esa.int' + nextpage_url)
def parse(self, response):
# iterate entries
for entry in response.css('div.launch-article'):
# create information container
item = ScrapyItem()
item['source'] = 'spacenews'
# retrieve publication date
temp_string = entry.css('time::text').extract_first()
# transfer time into ISO 8601
temp = timestring.Date(temp_string).date
item['date'] = temp.strftime("%Y-%m-%dT%H:%M:%S.%f%z")
# get abstract
item['brief'] = entry.css('p.post-excerpt::text').extract_first()
# get article url
item['url'] = entry.css('h2').css('a::attr(href)').extract_first()
# get article title
item['title'] = entry.css('h2').css('a::text').extract_first()
# check time
now = datetime.datetime.now()
now = now.strftime("%Y-%m-%dT%H:%M:%S.%f%z")
item['tstamp'] = now
# request to article page
request = scrapy.Request(item['url'], callback=self.parse_article)
request.meta['item'] = item
yield request
next_url = response.css('p.infinitescroll').css(
'a::attr(href)').extract_first()
if next_url:
yield scrapy.Request(next_url)
def parse(self, response):
# iterate entries
for entry in response.css('article.list-tpl__article'):
# retrieve info for our current post
item = ScrapyItem()
item['source'] = 'arianespace'
item['company'] = 'arianespace'
temp_string = entry.css(
'span.list-article__date::text').extract_first()
item['url'] = entry.css(
'a.list-article__title::attr(href)').extract_first()
item['title'] = entry.css(
'a.list-article__title::text').extract_first()
item['title'] = ' '.join(
item['title'].split()) #Extract \t\n symbols and alike
# get current time
now = datetime.datetime.now()
now = now.strftime("%Y-%m-%dT%H:%M:%S.%f%z")
item['tstamp'] = now
# convert article time to ISO 8601
temp = timestring.Date(temp_string).date
item['date'] = temp.strftime("%Y-%m-%dT%H:%M:%S.%f%z")
# get body and brief
request = scrapy.Request(item['url'],
callback=self.get_brief_body,
meta={'item': item})
request.meta['item'] = item
yield request
paginate = response.css('div.paginate').css('a')
for paginate_link in paginate:
if paginate_link.css('button.paginate__button--right'):
yield scrapy.Request(
paginate_link.css('::attr(href)').extract_first())
def parse(self, response):
# iterate entries
for entry in response.css('div.big__list__item__info'):
#retrieve info for our current post
item = ScrapyItem()
item['source'] = 'thales'
item['date'] = 'NotAvalaible'
item['brief'] = entry.css(
'div.field__item even::text').extract_first()
item['url'] = entry.css('a::attr(href)').extract_first()
item['title'] = entry.css('a::text').extract_first()
# check time
now = datetime.datetime.now()
item['tstamp'] = now
print(item)
yield item
def parse(self, response):
for entry in response.css('div.views-row'):
# Declare the container item
item = ScrapyItem()
item['source'] = 'spacex'
item['company'] = 'spacex'
# Extract the date
temp_string = entry.css('div.date::text').extract_first()
# transfer time into ISO 8601
temp = timestring.Date(temp_string).date
item['date'] = temp.strftime("%Y-%m-%dT%H:%M:%S.%f%z")
# Extract the title
item['title'] = entry.css('h2.title').css('a::text').extract_first()
# Extract the URL
item['url'] = 'http://www.spacex.com' + entry.css('h2.title').css('a::attr(href)').extract_first()
# Extract the brief
item['brief'] = entry.css('div.summary').css('p::text').extract_first()
# Save current time
now = datetime.datetime.now()
now = now.strftime("%Y-%m-%dT%H:%M:%S.%f%z")
item['tstamp'] = now
# Proceed to retrieve the body and the abstract
request = scrapy.Request(item['url'], callback=self.parse_body)
request.meta['item'] = item
yield request
# Go to next page if possible
nextpage_url = response.css('li.pager-next').css('a::attr(href)').extract_first()
if nextpage_url:
yield scrapy.Request('http://www.spacex.com' + nextpage_url)
def parse(self, response):
#iterate entries
for entry in response.css('div.pb-feed-headline.ng-scope'):
#retrieve info for our current post
item = ScrapyItem()
item['source'] = 'WP'
item['date'] = entry.css(
'span.pb-timestamp.ng-binding::text').extract_first()
item['brief'] = entry.css(
'div.pb-feed-description.ng-binding').extract_first()
item['url'] = entry.css('a.ng-binding::attr(href)').extract_first()
item['title'] = entry.css('a.ng-binding::text').extract_first()
# check time
now = datetime.datetime.now()
item['tstamp'] = now
print(item)
yield item
