def parse_item(self, response):
item = RssItem()
item.title = response.css(
'meta[property="og:title"]::attr(content)').get()
item.link = response.url
item.guid = response.url
item.pubDate = response.css(".title h6::text").get()
item.author = "Liberal Victoria"
item.description = "".join(response.css(".mr-content").extract())
yield item
def parse_item(self, response):
item = RssItem()
item.title = response.css("title::text").get().split(" - ",
1)[-1].strip()
item.link = response.url
item.guid = response.url
item.pubDate = response.css("div.newsCreatedDate::text").get().strip()
item.author = " & ".join(
response.css("img.ministersPic::attr(alt)").getall())
item.description = response.css("div.ms-rtestate-field").get()
yield item
def parse_item(self, response):
item = RssItem()
item.title = response.css(
'meta[name="dcterms.title"]::attr(content)').get()
item.link = response.url
item.guid = response.url
item.pubDate = response.css(
'meta[name="dcterms.issued"]::attr(content)').get()
item.author = response.css(
'meta[name="article.minister"]::attr(content)').get()
summary = response.css("div.news-detail__summary p").getall()
body = response.css("div.news-detail__body p").getall()
item.description = "".join(summary + body)
return item
def parse_item(self, response):
item = RssItem()
item.title = response.css("title::text").get().split(" | ")[0]
item.link = response.url
item.guid = response.url
item.pubDate = response.css(
'meta[name="dcterms.date"]::attr(content)').get()
item.description = response.css("div.nsw-wysiwyg-content").get()
author = response.css(
"div.standard-header__released_by div::text").getall()
if author:
item.author = author[-1].strip()
else:
item.author = "NSW Government"
yield item
def parse_item(self, response):
item = RssItem()
item.title = (
response.css('meta[name="DCTERMS.title"]::attr(content)').get().strip()
)
item.link = response.url
item.guid = response.url
item.pubDate = (
response.css("script::text")
.re_first(r'"datePublished": ".*"')
.split(":", 1)[-1]
.strip(' "')
)
author = response.css("p.statement-ministers::text").getall()
item.author = " & ".join(author)
description = response.css("div div p").getall()
cutoff = 2 # publish date & author
if len(author) > 1:
cutoff += len(author)
item.description = "".join(description[cutoff:])
yield item