def parse(self, response):
for titulo in response.xpath('.//div'):
item = RssItem()
item.title = titulo.xpath('.//a/text()').extract_first()
item.link = titulo.xpath('.//a/@href').extract_first()
yield item
def parse_products(self, response):
items = response.xpath('.//*')
for item in items:
product = RssItem()
title = 'prueba linkedin'
url = item.xpath('.//a/@href').extract_first()
product.title = title
product.link = url
yield product
def parse_products(self, response):
items = response.xpath('//ul[contains(@class, "itemsList")]/li')
for item in items:
product = RssItem()
title = item.xpath('.//h3/a/text()').extract_first().strip()
url = item.xpath('.//h3/a/@href').extract_first()
product_id = item.xpath('.//input[@name="id"]/@value').extract_first()
price = item.xpath('.//span[@class="currencyPrice"]/text()').extract_first()
product.title = title
product.link = url
product.description = price
yield product
def parse(self, response):
post_elements = response.css(
".cff-item.author-lnp---liberal-national-party")
for post in post_elements:
is_video_post = True if post.css(".cff-video-post") else False
item = RssItem()
item.author = post.css("div.cff-page-name a::text").get()
item.pubDate = post.css(".cff-date::text").get().strip()
item.link = post.css(".cff-viewpost-facebook::attr(href)").get()
item.guid = item.link.link
if is_video_post:
item.title = post.css(".cff-poster::attr(alt)").get()
item.description = post
else:
item.title = post.css(".cff-post-desc::text").get()
item.description = post.css(".cff-post-desc").get()
yield item
def parse_item(self, response):
item = RssItem()
item.title = response.css("title::text").get()
item.author = "Liberal Party of Western Australia"
item.link = response.url
item.guid = response.url
item.pubDate = response.css(
'meta[property="article:published_time"]::attr(content)').get()
item.description = response.css(".entry-content").get()
yield item
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("h4::text").get().strip()
item.author = response.css("div.header h1::text").get()
item.description = "".join(
response.css('div[style="width:100%"] p').getall())
yield item
def parse_item(self, response):
item = RssItem()
item.title = response.css(
'meta[property="og:description"]::attr(content)').get()
item.author = "South Australian Labor"
item.link = response.url
item.guid = response.url
item.pubDate = response.css(".timestampContent").get()
item.description = "".join(
response.css('div[data-testid="post_message"]').getall())
yield item
def parse_item(self, response):
item = RssItem()
item.title = response.css(
'meta[property="og:title"]::attr(content)').get()
item.author = " & ".join(
response.css(".contributor .name::text").getall())
item.pubDate = response.css(
'meta[property="article:published_time"]::attr(content)').get()
item.link = response.url
item.guid = response.url
item.description = response.css(".content").get()
yield item
def parse_item(self, response):
item = RssItem()
item.title = response.css("title::text").get().rsplit(" - ", 1)[0]
item.author = "Tasmanian Labor"
item.link = response.url
item.guid = response.url
item.pubDate = response.css(
'meta[property="article:published_time"]::attr(content)').get()
description = response.css(".content-body").get()
description = re.sub(r"<h2>.*?</h2>.*<time>.*?</time>", "",
description)
item.description = description
yield item
def parse_item(self, response):
date_pattern = (
r'field_news_date:"\d{4}-\d{2}-\d{2}T\d{2}:\d{2}:\d{2}\+\d{2}:\d{2}"'
)
item = RssItem()
item.title = response.css("title::text").get().split(" | ")[0]
item.link = response.url
item.guid = response.url
item.pubDate = (
response.css("script::text")
.re_first(date_pattern)
.split(":", maxsplit=1)[-1]
.strip('"')
)
item.description = "".join(response.css("div.rpl-markup__inner p").getall())
item.author = "State Government of Victoria"
yield item
def parse_item(self, response):
item = RssItem()
item.title = response.css('font[size="5"]::text').get()
item.link = response.url
item.guid = response.url
item.author = " - ".join(
response.css('font[size="6"]::text').getall()).strip()
re_date = r"\d{1,2} [A-Z][a-z]+ \d{4}"
item.pubDate = response.css(".paragraph").re_first(re_date)
description = response.css("div.content-wrap .paragraph").get()
description = re.sub(
f"<strong>(<span .*?>)?<font .*?>{item.title.title}(<br>)?</font>(</span>)?</strong><br>",
"",
description,
)
description = re.sub(re_date + "<br><br>", "", description)
item.description = description
yield item
def parse(self, response):
for category_name in response.css('.list-group-item ::text'):
item = RssItem()
item.title = category_name.extract()
yield item
def __init__(self, *args, **kwargs):
super(self.__class__, self).__init__(*args, **kwargs)
self.rss = RssItem()