---
name: wsj-article-extraction
description: Extract and summarize WSJ articles using multi-engine search when paywall blocks direct access
category: research
---

# WSJ Article Extraction Skill

## Trigger
Any request to summarize, analyze, or read content from a WSJ (Wall Street Journal) article URL.

## Problem
WSJ articles are behind a hard paywall. Direct access returns 403/blocked. Standard web scraping fails.

## Workflow (in order)

### Step 1: Extract article metadata from URL
Parse the URL slug to identify article title, section, and author:
- `https://on.wsj.com/4n2s9Ww` → short URL, need to resolve or search
- `https://www.wsj.com/sports/sabastian-sawe-london-marathon-world-record-08a842d8` → slug contains title + article ID

### Step 2: Bing News Search (primary)
Use bing news search for the article title to get snippet/摘要:
```
https://www.bing.com/search?q=+site:wsj.com+{TITLE}&format=rss
```
Or use the bing_news_search tool with query like `site:wsj.com {article title}`.

### Step 3: Yahoo Search (fallback)
```
https://search.yahoo.com/search?p={article_title}+site:wsj.com
```
Yahoo often shows article snippets in search results without paywall.

### Step 4: MSN/World Athletics/Other syndication
Search for same article on MSN, MarketWatch, or World Athletics (for sports):
```
https://www.bing.com/search?q={article_title}
```
Many WSJ articles get syndicated to MSN with full content visible.

### Step 5: World Athletics (sports only)
For running/athletics articles, World Athletics often has direct coverage:
```
https://worldathletics.org/news/
```

### Step 6: Extract from search snippets
Even if full article is blocked, search results typically show:
- Article title and subtitle
- Author byline
- Publication date
- Key quotes and statistics in the snippet

## Key Patterns Noted
- WSJ articles on legal/court cases often show outcomes in search snippets
- Sports articles (London Marathon, etc.) frequently syndicated to World Athletics
- Financial articles sometimes on MarketWatch with more accessible versions
- Bing News format=rss sometimes returns structured data

## Verification
Confirm article topic/source/date from search results before claiming analysis.

## Limitations
- Full article content may not be available
- Use available snippets to reconstruct main points
- Note in response when article has paywall and content is limited to search data