Class: SakamichiScraper::Sakurazaka
- Inherits:
-
Base
- Object
- Base
- SakamichiScraper::Sakurazaka
show all
- Defined in:
- lib/sakamichi_scraper/sakurazaka.rb
Instance Method Summary
collapse
Methods inherited from Base
#blog_list_page, #blog_top_page, #download_images_from_url_list, #exclude_img_path, #exec_date, #format_content, #format_timestamp, #get_content, #image_file_path, #image_urls_from_article_url, #init_url_from_yml, #mkdir_today_file_path
Constructor Details
Returns a new instance of Sakurazaka.
5
6
7
|
# File 'lib/sakamichi_scraper/sakurazaka.rb', line 5
def initialize
super("sakurazaka")
end
|
Instance Method Details
#blog_top_page_title ⇒ Object
9
10
11
|
# File 'lib/sakamichi_scraper/sakurazaka.rb', line 9
def blog_top_page_title
Nokogiri::HTML.parse(blog_top_page, nil, nil).title
end
|
#newest_blog_title ⇒ Object
13
14
15
|
# File 'lib/sakamichi_scraper/sakurazaka.rb', line 13
def newest_blog_title
Nokogiri.parse(blog_list_page, nil, nil).at_css(".date-title > .title").children.to_s
end
|
#picture_in_newest_article ⇒ Object
29
30
31
32
33
34
35
36
|
# File 'lib/sakamichi_scraper/sakurazaka.rb', line 29
def picture_in_newest_article
newest_article_url = article_urls_from_list_page(blog_list_page).first
article_html = get_content(newest_article_url)
image_urls = image_urls_from_article_url(article_html, "div.box-article")
mkdir_today_file_path unless Dir.exist?(image_file_path)
download_images_from_url_list(image_urls)
end
|
#recent_blog_info ⇒ Object
17
18
19
20
21
22
23
24
25
26
27
|
# File 'lib/sakamichi_scraper/sakurazaka.rb', line 17
def recent_blog_info
res = []
Nokogiri.parse(blog_list_page, nil, nil).css(".com-blog-part.box4.fxpc > li").each do |c|
info = {
member: c.css(".prof-in.fx > .name").children.to_s,
title: c.css(".date-title > .title").children.to_s,
timestamp: c.css(".date.wf-a").children.to_s
}
res << info
end
end
|