]>
Commit | Line | Data |
---|---|---|
4e067cea NL |
1 | title://h1[@class="articleHeadline"] |
2 | body://div[@id="article"] | |
3 | body://*[@itemprop="articleBody"] | |
4 | strip_id_or_class:articleTools | |
5 | strip_id_or_class:readerscomment | |
6 | #strip://div[contains(@class, "articleInline runaroundLeft")] | |
7 | strip: //div[contains(@class, "doubleRule")] | |
8 | # strip image credit - appears as a bold heading | |
9 | strip: //div[contains(@class, "articleInline")]//h6 | |
10 | strip_id_or_class:enlargeThis | |
11 | strip_id_or_class:pageLinks | |
12 | strip_id_or_class:memberTools | |
13 | strip_id_or_class:articleExtras | |
14 | strip_id_or_class:singleAd | |
15 | strip_id_or_class:byline | |
16 | strip_id_or_class:dateline | |
17 | strip_id_or_class:articleheadline | |
18 | strip_id_or_class:articleBottomExtra | |
19 | strip_id_or_class:shareTools | |
20 | strip://a[contains(@href, 'nytimes.com/adx/')] | |
21 | strip: //nyt_byline | |
22 | strip: //span[contains(@class, 'slideshow') or contains(@class, 'video')] | |
23 | strip: //p[@class='caption']//a[contains(., 'More Photos')] | |
24 | ||
25 | prune: no | |
26 | tidy: no | |
27 | ||
28 | find_string: <script | |
29 | replace_string: <div style="display:none" | |
30 | find_string: </script> | |
31 | replace_string: </div> | |
32 | ||
33 | date: substring-after(//*[contains(@class, 'dateline')], 'Published:') | |
34 | ||
35 | single_page_link: //link[contains(@href, 'pagewanted=all')] | |
36 | single_page_link: //link[@rel='alternate' and contains(@href, 'mobile.nytimes.com')]/@href | |
37 | single_page_link: concat(substring-before(//div[@id='pageLinks']//a[contains(@href, 'pagewanted=')]/@href, 'pagewanted='), 'pagewanted=all') | |
38 | #single_page_link: //a[contains(@href, 'pagewanted=all') and not(contains(@href, 'login'))] | |
39 | ||
40 | strip://ul[@id = 'toolsList'] | |
41 | strip://h6[@class = 'kicker'] | |
42 | author:substring-after(//h6[@class='byline'],'By ') | |
43 | ||
44 | test_url: http://www.nytimes.com/2011/07/24/books/review/an-academic-authors-unintentional-masterpiece.html | |
45 | test_url: http://www.nytimes.com/2012/06/10/arts/television/the-newsroom-aaron-sorkins-return-to-tv.html | |
46 | test_url: http://www.nytimes.com/2013/03/25/world/middleeast/israeli-military-responds-after-patrols-come-under-fire-from-syria.html | |
47 | test_url: http://www.nytimes.com/2013/08/15/nyregion/when-the-new-york-city-subway-ran-without-rails.html | |
48 | test_url: http://www.nytimes.com/2004/02/29/weekinreview/correspondence-class-consciousness-china-s-wealthy-live-creed-hobbes-darwin-meet.html | |
49 | test_url: http://www.nytimes.com/2014/06/19/opinion/gail-collins-romney-and-the-2016-contenders-huddle.html |