Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[EconomistBridge] Fixes for fetching new page structure #1836

Merged
merged 8 commits into from
Nov 29, 2020
Merged

[EconomistBridge] Fixes for fetching new page structure #1836

Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
f7c71f6
[EconomistBridge] Added new bridge
thefranke Mar 15, 2019
61b01c6
[EconomistBridge] Use cached fetch for articles
thefranke Mar 15, 2019
ba71fe5
[EconomistBridge] Fix TravisCI issues
thefranke Mar 17, 2019
ddb79a8
[EconomistBridge] Added PR suggestions
thefranke Mar 17, 2019
b37d9bd
[EconomistBridge] Fix count of items
thefranke Mar 29, 2019
9e11ddc
Merge branch 'master' of https://github.com/RSS-Bridge/rss-bridge int…
thefranke Nov 3, 2020
b038a2b
Fix EconomistBridge to account for new page structure
thefranke Nov 3, 2020
f3370a5
PR fixes
thefranke Nov 22, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
35 changes: 21 additions & 14 deletions bridges/EconomistBridge.php
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,17 +14,28 @@ public function collectData() {
$html = getSimpleHTMLDOM(self::URI . '/latest/')
or returnServerError('Could not fetch latest updates form The Economist.');

foreach($html->find('article') as $element) {
foreach($html->find('div.teaser') as $element) {

$a = $element->find('a.headline-link', 0);
$href = $a->href;

if (substr($href, 0, 4) != 'http')
$href = self::URI . $a->href;

$a = $element->find('a', 0);
$href = self::URI . $a->href;
$full = getSimpleHTMLDOMCached($href);
$article = $full->find('article', 0);
$header = $article->find('span[itemprop="headline"]', 0);
$headerimg = $article->find('div[itemprop="image"]', 0)->find('img', 0);
$author = $article->find('p[itemprop="byline"]', 0);
$time = $article->find('time', 0);
$content = $article->find('div[itemprop="text"]', 0);
$section = array( $article->find('strong[itemprop="articleSection"]', 0)->plaintext );

$header = $article->find('h1', 0);
$author = $article->find('span[itemprop="author"]', 0);
$time = $article->find('time[itemprop="dateCreated"]', 0);
$content = $article->find('div[itemprop="description"]', 0);
// Author
if ($author)
$author = substr($author->innertext, 3, strlen($author));
else
$author = 'The Economist';

// Remove newsletter subscription box
$newsletter = $content->find('div[class="newsletter-form__message"]', 0);
Expand All @@ -40,19 +51,15 @@ public function collectData() {
if ($nextprev)
$nextprev->outertext = '';

$section = array( $article->find('h3[itemprop="articleSection"]', 0)->plaintext );

$item = array();
$item['title'] = $header->find('span', 0)->innertext . ': '
. $header->find('span', 1)->innertext;

$item['title'] = $header->innertext;
$item['uri'] = $href;
$item['timestamp'] = strtotime($time->datetime);
$item['author'] = $author->innertext;
$item['author'] = $author;
$item['categories'] = $section;

$item['content'] = '<img style="max-width: 100%" src="'
. $a->find('img', 0)->src . '">' . $content->innertext;
. $headerimg->src . '">' . $content->innertext;

$this->items[] = $item;

Expand Down