Skip to content

Commit 0ccb91a

Browse files
authored
release: 2.2.1 (#631)
1 parent 8c99822 commit 0ccb91a

4 files changed

Lines changed: 70 additions & 6 deletions

File tree

CHANGELOG.md

Lines changed: 15 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,20 @@
11
# Mercury Parser Changelog
22

3+
### 2.2.1 (Sept 08, 2020)
4+
5+
##### Commits
6+
7+
- [[`8c9982247b`](https://github.com/postlight/mercury-parser/commit/8c9982247b)] - **feat**: Ladbible.com extractor (#624) (Nitin Khanna)
8+
- [[`30d6f472ee`](https://github.com/postlight/mercury-parser/commit/30d6f472ee)] - **feat**: Times of India extractor (#503) (Nitin Khanna)
9+
- [[`c15f4f5c3e`](https://github.com/postlight/mercury-parser/commit/c15f4f5c3e)] - chore(deps): bump lodash from 4.17.2 to 4.17.21 (#612) (dependabot[bot])
10+
- [[`b8b90afa95`](https://github.com/postlight/mercury-parser/commit/b8b90afa95)] - chore(deps): bump handlebars from 4.1.2 to 4.7.6 (#583) (dependabot[bot])
11+
- [[`38fb3204f5`](https://github.com/postlight/mercury-parser/commit/38fb3204f5)] - **chore**: remove greenkeeper configs (#580) (Jad Termsani)
12+
- [[`a5a066c69d`](https://github.com/postlight/mercury-parser/commit/a5a066c69d)] - **chore**: update node version (#579) (Jad Termsani)
13+
- [[`b0e708aac6`](https://github.com/postlight/mercury-parser/commit/b0e708aac6)] - **feat**: update nytimes extractor (#506) (Wajeeh Zantout)
14+
- [[`3fb8526c4a`](https://github.com/postlight/mercury-parser/commit/3fb8526c4a)] - chore(package): update ora to version 4.0.0 (#500) (greenkeeper[bot])
15+
- [[`3009ecf137`](https://github.com/postlight/mercury-parser/commit/3009ecf137)] - fix(package): update yargs-parser to version 14.0.0 (#495) (greenkeeper[bot])
16+
- [[`c5c000586d`](https://github.com/postlight/mercury-parser/commit/c5c000586d)] - **release**: 2.2.0 (#496) (Michael Ashley)
17+
318
### 2.2.0 (Sept 10, 2019)
419

520
##### Commits

dist/mercury.js

Lines changed: 53 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -1888,13 +1888,13 @@ var TwitterExtractor = {
18881888
var NYTimesExtractor = {
18891889
domain: 'www.nytimes.com',
18901890
title: {
1891-
selectors: ['h1.g-headline', 'h1[itemprop="headline"]', 'h1.headline']
1891+
selectors: ['h1.g-headline', 'h1[itemprop="headline"]', 'h1.headline', 'h1 .balancedHeadline']
18921892
},
18931893
author: {
1894-
selectors: [['meta[name="author"]', 'value'], '.g-byline', '.byline']
1894+
selectors: [['meta[name="author"]', 'value'], '.g-byline', '.byline', ['meta[name="byl"]', 'value']]
18951895
},
18961896
content: {
1897-
selectors: ['div.g-blocks', 'article#story'],
1897+
selectors: ['div.g-blocks', 'section[name="articleBody"]', 'article#story'],
18981898
transforms: {
18991899
'img.g-lazy': function imgGLazy($node) {
19001900
var src = $node.attr('src');
@@ -5767,6 +5767,53 @@ var EpaperZeitDeExtractor = {
57675767
}
57685768
};
57695769

5770+
var WwwLadbibleComExtractor = {
5771+
domain: 'www.ladbible.com',
5772+
title: {
5773+
selectors: ['h1']
5774+
},
5775+
author: {
5776+
selectors: ['[class*=Byline]']
5777+
},
5778+
date_published: {
5779+
selectors: ['time'],
5780+
timezone: 'Europe/London'
5781+
},
5782+
lead_image_url: {
5783+
selectors: [['meta[name="og:image"]', 'value']]
5784+
},
5785+
content: {
5786+
selectors: ['[class*=ArticleContainer]'],
5787+
clean: ['time', 'source', 'a[href^="https://www.ladbible.com/"]', 'picture', '[class*=StyledCardBlock]']
5788+
}
5789+
};
5790+
5791+
var TimesofindiaIndiatimesComExtractor = {
5792+
domain: 'timesofindia.indiatimes.com',
5793+
title: {
5794+
selectors: ['h1']
5795+
},
5796+
extend: {
5797+
reporter: {
5798+
selectors: ['div.byline'],
5799+
transforms: {}
5800+
}
5801+
},
5802+
date_published: {
5803+
selectors: ['.byline'],
5804+
format: 'MMM D, YYYY, HH:mm z',
5805+
timezone: 'Asia/Kolkata'
5806+
},
5807+
lead_image_url: {
5808+
selectors: [['meta[name="og:image"]', 'value']]
5809+
},
5810+
content: {
5811+
selectors: ['div.contentwrapper:has(section)'],
5812+
defaultCleaner: false,
5813+
clean: ['section', 'h1', '.byline', '.img_cptn']
5814+
}
5815+
};
5816+
57705817

57715818

57725819
var CustomExtractors = /*#__PURE__*/Object.freeze({
@@ -5903,7 +5950,9 @@ var CustomExtractors = /*#__PURE__*/Object.freeze({
59035950
WwwPhoronixComExtractor: WwwPhoronixComExtractor,
59045951
PitchforkComExtractor: PitchforkComExtractor,
59055952
BiorxivOrgExtractor: BiorxivOrgExtractor,
5906-
EpaperZeitDeExtractor: EpaperZeitDeExtractor
5953+
EpaperZeitDeExtractor: EpaperZeitDeExtractor,
5954+
WwwLadbibleComExtractor: WwwLadbibleComExtractor,
5955+
TimesofindiaIndiatimesComExtractor: TimesofindiaIndiatimesComExtractor
59075956
});
59085957

59095958
var Extractors = _Object$keys(CustomExtractors).reduce(function (acc, key) {

dist/mercury.web.js

Lines changed: 1 addition & 1 deletion
Some generated files are not rendered by default. Learn more about customizing how changed files appear on GitHub.

package.json

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -1,6 +1,6 @@
11
{
22
"name": "@postlight/mercury-parser",
3-
"version": "2.2.0",
3+
"version": "2.2.1",
44
"description": "Mercury transforms web pages into clean text. Publishers and programmers use it to make the web make sense, and readers use it to read any web article comfortably.",
55
"author": "Postlight <mercury@postlight.com>",
66
"homepage": "https://mercury.postlight.com",

0 commit comments

Comments
 (0)