Class: Hongkong::News::Scrapers::OrientalDailyScraper
- Inherits:
-
Object
- Object
- Hongkong::News::Scrapers::OrientalDailyScraper
- Includes:
- PhantomScraper
- Defined in:
- lib/hongkong/news/scrapers/oriental_daily_scraper.rb
Constant Summary collapse
- LIST_URL =
"http://orientaldaily.on.cc/"
Instance Method Summary collapse
- #name ⇒ Object
-
#news(url) ⇒ Object
Extract article from page.
-
#news_links ⇒ Object
Extract all news links.
Methods included from PhantomScraper
Instance Method Details
#name ⇒ Object
12 13 14 |
# File 'lib/hongkong/news/scrapers/oriental_daily_scraper.rb', line 12 def name "orientaldaily" end |
#news(url) ⇒ Object
Extract article from page
29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 |
# File 'lib/hongkong/news/scrapers/oriental_daily_scraper.rb', line 29 def news(url) visit url # wait for content to be loaded first("#contentCTN-right") document = Document.new document.source = name document.title = doc.search("h1").text document.url = url document.html = html document.content = page.evaluate_script("HongKongNews.getInnerText('#contentCTN-top')") + "\n" + page.evaluate_script("HongKongNews.getInnerText('#contentCTN-right')") document.screenshot_data = screenshot_data image = doc.search("#contentCTN .photo img").first document.image_url = URI::join(url, image["src"]).to_s if image document end |
#news_links ⇒ Object
Extract all news links
17 18 19 20 21 22 23 24 25 26 |
# File 'lib/hongkong/news/scrapers/oriental_daily_scraper.rb', line 17 def news_links visit LIST_URL all("#articleListSELECT option").collect do |option| link = Link.new link.title = option.text link.url = URI::join(LIST_URL, option["value"]).to_s link end.reject { |l| l.url.to_s.end_with?("#") } end |