gs-export

Name: gs-export
Author: cookjohn

175installs27forks

How to install gs-export?

cookjohn/gs-skills/gs-export

$npx -y skills add cookjohn/gs-skills --skill gs-export

Installs into the current project.

Summary

Export Google Scholar paper(s) to Zotero via BibTeX. Gets citation data from Google Scholar's cite dialog, then pushes to Zotero desktop. Supports single or batch export.

Files · 1

View on GitHub

SKILL.md

1	# Google Scholar Export to Zotero
2
3	Export Google Scholar paper citation data via BibTeX extraction and push to Zotero desktop.
4
5	## Arguments
6
7	$ARGUMENTS contains one or more data-cids (space-separated), e.g.:
8	- `TFS2GgoGiNUJ` — single paper
9	- `TFS2GgoGiNUJ abc123XYZ def456UVW` — batch export
10
11	## Steps
12
13	### Step 1: Get BibTeX for each paper
14
15	For each data-cid, perform 3 tool calls to bypass CORS:
16
17	#### 1a. Fetch cite dialog to get BibTeX link (evaluate_script)
18
19	```javascript
20	async () => {
21	const cid = "DATA_CID_HERE";
22	const resp = await fetch(
23	`https://scholar.google.com/scholar?q=info:${cid}:scholar.google.com/&output=cite`,
24	{ credentials: 'include' }
25	);
26	const html = await resp.text();
27	const doc = new DOMParser().parseFromString(html, 'text/html');
28
29	// Extract export links
30	const links = Array.from(doc.querySelectorAll('#gs_citi a')).map(a => ({
31	format: a.textContent.trim(),
32	url: a.href
33	}));
34
35	// Extract citation format texts
36	const citations = Array.from(doc.querySelectorAll('#gs_citt tr')).map(tr => {
37	const cells = tr.querySelectorAll('td');
38	return {
39	style: cells[0]?.textContent?.trim() \|\| '',
40	text: cells[1]?.textContent?.trim() \|\| ''
41	};
42	});
43
44	const bibtexLink = links.find(l => l.format === 'BibTeX');
45	return { cid, bibtexLink: bibtexLink?.url \|\| '', links, citations };
46	}
47	```
48
49	#### 1b. Navigate to BibTeX URL (navigate_page)
50
51	Use `mcp__chrome-devtools__navigate_page`:
52	- url: the `bibtexLink` URL from step 1a (on `scholar.googleusercontent.com`)
53
54	This bypasses CORS restrictions that block fetch() to googleusercontent.com.
55
56	#### 1c. Read BibTeX content (evaluate_script)
57
58	```javascript
59	async () => {
60	return { bibtex: document.body.innerText \|\| document.body.textContent \|\| '' };
61	}
62	```
63
64	### Step 2: Parse BibTeX and push to Zotero
65
66	Save the BibTeX data as JSON, then call the push script:
67
68	```bash
69	python "E:/gscholar-skills/.claude/skills/gs-export/scripts/push_to_zotero.py" /tmp/gs_papers.json
70	```
71
72	Before calling the script, construct a JSON file at `/tmp/gs_papers.json` containing paper data parsed from BibTeX. Parse the BibTeX yourself and create the JSON array:
73
74	```json
75	[
76	{
77	"pmid": "",
78	"title": "The title from BibTeX",
79	"authors": [
80	{"lastName": "Smith", "firstName": "John"}
81	],
82	"journal": "Journal Name",
83	"journalAbbr": "",
84	"pubdate": "2022",
85	"volume": "14",
86	"issue": "4",
87	"pages": "1054",
88	"doi": "",
89	"pdfUrl": "https://example.com/paper.pdf",
90	"abstract": "",
91	"keywords": [],
92	"language": "en",
93	"pubtype": ["Journal Article"]
94	}
95	]
96	```
97
98	IMPORTANT: Set `pdfUrl` from the search result's `fullTextUrl` field (the PDF link extracted by gs-search). The Python script will download the PDF and upload it to Zotero via `/connector/saveAttachment` (Zotero 7.x ignores attachments in saveItems). PDF download may fail for some publishers (403, JS-redirect); these are reported as "PDF skip".
99
100	BibTeX fields mapping:
101	- `@article{key,` → `itemType: journalArticle`
102	- `@inproceedings{key,` → `itemType: conferencePaper`
103	- `@book{key,` → `itemType: book`
104	- `title={...}` → `title`
105	- `author={Last1, First1 and Last2, First2}` → `authors` array
106	- `journal={...}` → `journal`
107	- `year={...}` → `pubdate`
108	- `volume={...}` → `volume`
109	- `number={...}` → `issue`
110	- `pages={...}` → `pages`
111	- `publisher={...}` → (included in extra or publisher field)
112
113	### Step 3: Report
114
115	Single paper:
116	```
117	Exported to Zotero from Google Scholar:
118	Title: {title}
119	Authors: {authors}
120	Journal: {journal} ({year})
121	Data-CID: {dataCid}
122	```
123
124	Batch:
125	```
126	Exported {count} papers to Zotero from Google Scholar:
127	1. {title1} ({journal1}, {year1})
128	2. {title2} ({journal2}, {year2})
129	...
130	```
131
132	## Batch Export Optimization
133
134	For multiple papers, process sequentially to avoid CAPTCHA:
135	1. Get all BibTeX links in one evaluate_script call (fetch all cite dialogs)
136	2. Navigate to each BibTeX URL one at a time
137	3. Collect all BibTeX entries
138	4. Push all to Zotero in a single batch
139
140	## Notes
141
142	- Single paper export uses 3-4 tool calls: `evaluate_script` (cite dialog) + `navigate_page` (BibTeX URL) + `evaluate_script` (read BibTeX) + `bash python` (Zotero push)
143	- Batch export: 2N+1 tool calls (N papers: N navigate + N evaluate + 1 bash)
144	- BibTeX links are on `scholar.googleusercontent.com` — CORS blocks fetch(), so we use navigate_page to bypass
145	- Reuses `push_to_zotero.py` for Zotero Connector API communication
146	- Google Scholar BibTeX does NOT include abstract or DOI — these fields will be empty in Zotero
147	- After export, navigate back to Google Scholar page: `navigate_page` with type `back`

People who liked this also viewed

6 picks

Type

azure-aiUse for Azure AI: Search, Speech, OpenAI, Document Intelligence. Helps with search, vector/hybrid search, speech-to-text, text-to-speech, transcription, OCR. WHEN: AI Search, query search, vector searSkillsJul 2026472k1.3k
just-scrapeSearch, scrape, crawl, extract structured data, and monitor web pages via the ScrapeGraph AI CLI. Use when the user asks to search the web, scrape a webpage, grab content from a URL, extract JSON fromSkillsJul 2026245k37
firecrawlCLI and Agent Skill for Firecrawl - Add scrape, search, and browsing capabilities to your AI agentsSkillsJul 202694k531
firecrawl-searchWeb search with full page content extraction. Use this skill whenever the user asks to search the web, find articles, research a topic, look something up, find recent news, discover sources, or says "SkillsJul 202676k531
firecrawl-agentAI-powered autonomous data extraction that navigates complex sites and returns structured JSON. Use this skill when the user wants structured data from websites, needs to extract pricing tiers, producSkillsJul 202674k531
firecrawl-mapDiscover and list all URLs on a website, with optional search filtering. Use this skill when the user wants to find a specific page on a large site, list all URLs, see the site structure, find where sSkillsJul 202674k531

gs-export

175installs27forks

View on GitHub

How to install gs-export?

cookjohn/gs-skills/gs-export

$npx -y skills add cookjohn/gs-skills --skill gs-export

Installs into the current project.

Summary

Export Google Scholar paper(s) to Zotero via BibTeX. Gets citation data from Google Scholar's cite dialog, then pushes to Zotero desktop. Supports single or batch export.

Files · 1

View on GitHub

SKILL.md

1	# Google Scholar Export to Zotero
2
3	Export Google Scholar paper citation data via BibTeX extraction and push to Zotero desktop.
4
5	## Arguments
6
7	$ARGUMENTS contains one or more data-cids (space-separated), e.g.:
8	- `TFS2GgoGiNUJ` — single paper
9	- `TFS2GgoGiNUJ abc123XYZ def456UVW` — batch export
10
11	## Steps
12
13	### Step 1: Get BibTeX for each paper
14
15	For each data-cid, perform 3 tool calls to bypass CORS:
16
17	#### 1a. Fetch cite dialog to get BibTeX link (evaluate_script)
18
19	```javascript
20	async () => {
21	const cid = "DATA_CID_HERE";
22	const resp = await fetch(
23	`https://scholar.google.com/scholar?q=info:${cid}:scholar.google.com/&output=cite`,
24	{ credentials: 'include' }
25	);
26	const html = await resp.text();
27	const doc = new DOMParser().parseFromString(html, 'text/html');
28
29	// Extract export links
30	const links = Array.from(doc.querySelectorAll('#gs_citi a')).map(a => ({
31	format: a.textContent.trim(),
32	url: a.href
33	}));
34
35	// Extract citation format texts
36	const citations = Array.from(doc.querySelectorAll('#gs_citt tr')).map(tr => {
37	const cells = tr.querySelectorAll('td');
38	return {
39	style: cells[0]?.textContent?.trim() \|\| '',
40	text: cells[1]?.textContent?.trim() \|\| ''
41	};
42	});
43
44	const bibtexLink = links.find(l => l.format === 'BibTeX');
45	return { cid, bibtexLink: bibtexLink?.url \|\| '', links, citations };
46	}
47	```
48
49	#### 1b. Navigate to BibTeX URL (navigate_page)
50
51	Use `mcp__chrome-devtools__navigate_page`:
52	- url: the `bibtexLink` URL from step 1a (on `scholar.googleusercontent.com`)
53
54	This bypasses CORS restrictions that block fetch() to googleusercontent.com.
55
56	#### 1c. Read BibTeX content (evaluate_script)
57
58	```javascript
59	async () => {
60	return { bibtex: document.body.innerText \|\| document.body.textContent \|\| '' };
61	}
62	```
63
64	### Step 2: Parse BibTeX and push to Zotero
65
66	Save the BibTeX data as JSON, then call the push script:
67
68	```bash
69	python "E:/gscholar-skills/.claude/skills/gs-export/scripts/push_to_zotero.py" /tmp/gs_papers.json
70	```
71
72	Before calling the script, construct a JSON file at `/tmp/gs_papers.json` containing paper data parsed from BibTeX. Parse the BibTeX yourself and create the JSON array:
73
74	```json
75	[
76	{
77	"pmid": "",
78	"title": "The title from BibTeX",
79	"authors": [
80	{"lastName": "Smith", "firstName": "John"}
81	],
82	"journal": "Journal Name",
83	"journalAbbr": "",
84	"pubdate": "2022",
85	"volume": "14",
86	"issue": "4",
87	"pages": "1054",
88	"doi": "",
89	"pdfUrl": "https://example.com/paper.pdf",
90	"abstract": "",
91	"keywords": [],
92	"language": "en",
93	"pubtype": ["Journal Article"]
94	}
95	]
96	```
97
98	IMPORTANT: Set `pdfUrl` from the search result's `fullTextUrl` field (the PDF link extracted by gs-search). The Python script will download the PDF and upload it to Zotero via `/connector/saveAttachment` (Zotero 7.x ignores attachments in saveItems). PDF download may fail for some publishers (403, JS-redirect); these are reported as "PDF skip".
99
100	BibTeX fields mapping:
101	- `@article{key,` → `itemType: journalArticle`
102	- `@inproceedings{key,` → `itemType: conferencePaper`
103	- `@book{key,` → `itemType: book`
104	- `title={...}` → `title`
105	- `author={Last1, First1 and Last2, First2}` → `authors` array
106	- `journal={...}` → `journal`
107	- `year={...}` → `pubdate`
108	- `volume={...}` → `volume`
109	- `number={...}` → `issue`
110	- `pages={...}` → `pages`
111	- `publisher={...}` → (included in extra or publisher field)
112
113	### Step 3: Report
114
115	Single paper:
116	```
117	Exported to Zotero from Google Scholar:
118	Title: {title}
119	Authors: {authors}
120	Journal: {journal} ({year})
121	Data-CID: {dataCid}
122	```
123
124	Batch:
125	```
126	Exported {count} papers to Zotero from Google Scholar:
127	1. {title1} ({journal1}, {year1})
128	2. {title2} ({journal2}, {year2})
129	...
130	```
131
132	## Batch Export Optimization
133
134	For multiple papers, process sequentially to avoid CAPTCHA:
135	1. Get all BibTeX links in one evaluate_script call (fetch all cite dialogs)
136	2. Navigate to each BibTeX URL one at a time
137	3. Collect all BibTeX entries
138	4. Push all to Zotero in a single batch
139
140	## Notes
141
142	- Single paper export uses 3-4 tool calls: `evaluate_script` (cite dialog) + `navigate_page` (BibTeX URL) + `evaluate_script` (read BibTeX) + `bash python` (Zotero push)
143	- Batch export: 2N+1 tool calls (N papers: N navigate + N evaluate + 1 bash)
144	- BibTeX links are on `scholar.googleusercontent.com` — CORS blocks fetch(), so we use navigate_page to bypass
145	- Reuses `push_to_zotero.py` for Zotero Connector API communication
146	- Google Scholar BibTeX does NOT include abstract or DOI — these fields will be empty in Zotero
147	- After export, navigate back to Google Scholar page: `navigate_page` with type `back`

People who liked this also viewed

6 picks

Type