diff options
author | Frédéric Guillot <fred@miniflux.net> | 2017-12-10 20:51:04 -0800 |
---|---|---|
committer | Frédéric Guillot <fred@miniflux.net> | 2017-12-10 20:51:04 -0800 |
commit | 87ccad5c7f1edf8bce37af547ca1659326398fa8 (patch) | |
tree | 4998a78ac68b1c2c03e6152d26567928cdf042ec /reader/scraper/rules.go | |
parent | 7a35c58f53d76356292e3e0ca9c91add3595a9e0 (diff) |
Add scraper rules
Diffstat (limited to 'reader/scraper/rules.go')
-rw-r--r-- | reader/scraper/rules.go | 16 |
1 files changed, 16 insertions, 0 deletions
diff --git a/reader/scraper/rules.go b/reader/scraper/rules.go new file mode 100644 index 0000000..ae6c4a5 --- /dev/null +++ b/reader/scraper/rules.go @@ -0,0 +1,16 @@ +// Copyright 2017 Frédéric Guillot. All rights reserved. +// Use of this source code is governed by the Apache 2.0 +// license that can be found in the LICENSE file. + +package scraper + +// List of predefined scraper rules (alphabetically sorted) +// domain => CSS selectors +var predefinedRules = map[string]string{ + "lemonde.fr": "div#articleBody", + "lesjoiesducode.fr": ".blog-post-content img", + "linux.com": "div.content, div[property]", + "opensource.com": "div[property]", + "phoronix.com": "div.content", + "techcrunch.com": "div.article-entry", +} |