Skip to content

Commit f6a1967

Browse files
VinciGit00VinciGit00
committed
refactoring of the javascript code
1 parent da98f8f commit f6a1967

File tree

9 files changed

+106
-13
lines changed

9 files changed

+106
-13
lines changed

‎cookbook/chat-webpage-simple-rag/scrapegraph_burr_lancedb.ipynb‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -544,8 +544,8 @@
544544
"text": [
545545
"The founders of ScrapeGraphAI are:\n",
546546
"\n",
547-
"1. **Marco Perini** - Founder & Technical Lead\n",
548-
" - [LinkedIn profile of Marco Perini](https://www.linkedin.com/in/perinim/)\n",
547+
"1. **** - Founder & Technical Lead\n",
548+
" - [LinkedIn profile of ](https://www.linkedin.com/in/perinim/)\n",
549549
"\n",
550550
"2. **Marco Vinciguerra** - Founder & Software Engineer\n",
551551
" - [LinkedIn profile of Marco Vinciguerra](https://www.linkedin.com/in/marco-vinciguerra-7ba365242/)\n",

‎cookbook/company-info/scrapegraph_langchain.ipynb‎

Lines changed: 1 addition & 1 deletion
Large diffs are not rendered by default.

‎cookbook/company-info/scrapegraph_llama_index.ipynb‎

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -651,7 +651,7 @@
651651
{
652652
"data": {
653653
"application/vnd.google.colaboratory.intrinsic+json": {
654-
"summary": "{\n \"name\": \"df_founders\",\n \"rows\": 3,\n \"fields\": [\n {\n \"column\": \"name\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 3,\n \"samples\": [\n \"Marco Perini\",\n \"Marco Vinciguerra\",\n \"Lorenzo Padoan\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"role\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 3,\n \"samples\": [\n \"Founder & Technical Lead\",\n \"Founder & Software Engineer\",\n \"Founder & Product Engineer\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"linkedin\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 3,\n \"samples\": [\n \"https://www.linkedin.com/in/perinim/\",\n \"https://www.linkedin.com/in/marco-vinciguerra-7ba365242/\",\n \"https://www.linkedin.com/in/lorenzo-padoan-4521a2154/\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}",
654+
"summary": "{\n \"name\": \"df_founders\",\n \"rows\": 3,\n \"fields\": [\n {\n \"column\": \"name\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 3,\n \"samples\": [\n \"\",\n \"Marco Vinciguerra\",\n \"Lorenzo Padoan\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"role\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 3,\n \"samples\": [\n \"Founder & Technical Lead\",\n \"Founder & Software Engineer\",\n \"Founder & Product Engineer\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n },\n {\n \"column\": \"linkedin\",\n \"properties\": {\n \"dtype\": \"string\",\n \"num_unique_values\": 3,\n \"samples\": [\n \"https://www.linkedin.com/in/perinim/\",\n \"https://www.linkedin.com/in/marco-vinciguerra-7ba365242/\",\n \"https://www.linkedin.com/in/lorenzo-padoan-4521a2154/\"\n ],\n \"semantic_type\": \"\",\n \"description\": \"\"\n }\n }\n ]\n}",
655655
"type": "dataframe",
656656
"variable_name": "df_founders"
657657
},
@@ -684,7 +684,7 @@
684684
" <tbody>\n",
685685
" <tr>\n",
686686
" <th>0</th>\n",
687-
" <td>Marco Perini</td>\n",
687+
" <td></td>\n",
688688
" <td>Founder &amp; Technical Lead</td>\n",
689689
" <td>https://www.linkedin.com/in/perinim/</td>\n",
690690
" </tr>\n",
@@ -970,7 +970,7 @@
970970
],
971971
"text/plain": [
972972
" name role \\\n",
973-
"0 Marco Perini Founder & Technical Lead \n",
973+
"0 Founder & Technical Lead \n",
974974
"1 Marco Vinciguerra Founder & Software Engineer \n",
975975
"2 Lorenzo Padoan Founder & Product Engineer \n",
976976
"\n",

‎cookbook/company-info/scrapegraph_sdk.ipynb‎

Lines changed: 1 addition & 1 deletion
Large diffs are not rendered by default.

‎scrapegraph-js/examples/sendFeedback_example.js‎

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -12,3 +12,9 @@ try {
1212
} catch (error) {
1313
console.error(error);
1414
}
15+
16+
const apiKey = 'your-api-key';
17+
const requestId = 'your-request-id';
18+
getSearchScraperRequest(apiKey, requestId)
19+
.then(data => console.log(data))
20+
.catch(error => console.error(error));

‎scrapegraph-js/src/markdownify.js‎

Lines changed: 32 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -33,8 +33,38 @@ export async function markdownify(apiKey, url) {
3333
*
3434
* @param {string} apiKey - Your ScrapeGraph AI API key.
3535
* @param {string} requestId - The unique identifier for the markdownify request whose result you want to retrieve.
36-
* @returns {Promise<string>} A promise that resolves with details about the status or outcome of the specified request.
37-
* @throws {Error} Throws an error if the HTTP request fails.
36+
* @returns {Promise<Object>} A promise that resolves to an object containing:
37+
* - status: The current status of the request ('pending', 'completed', 'failed')
38+
* - result: The markdown content when status is 'completed'
39+
* - error: Error message if the request failed (when status is 'failed')
40+
* - created_at: Timestamp of when the request was created
41+
* - completed_at: Timestamp of when the request was completed (if applicable)
42+
* @throws {Error} Throws an error if the HTTP request fails or if the API key is invalid
43+
*
44+
* @example
45+
* // Example usage:
46+
* const apiKey = 'your-api-key';
47+
* const requestId = 'previously-obtained-request-id';
48+
*
49+
* try {
50+
* const result = await getMarkdownifyRequest(apiKey, requestId);
51+
* if (result.status === 'completed') {
52+
* console.log('Markdown content:', result.result);
53+
* } else if (result.status === 'pending') {
54+
* console.log('Conversion is still in progress');
55+
* } else {
56+
* console.log('Conversion failed:', result.error);
57+
* }
58+
* } catch (error) {
59+
* console.error('Error fetching markdown:', error);
60+
* }
61+
*
62+
* @note The markdown content includes:
63+
* - Properly formatted headers
64+
* - Lists and tables
65+
* - Code blocks with language detection
66+
* - Links and images
67+
* - Text formatting (bold, italic, etc.)
3868
*/
3969
export async function getMarkdownifyRequest(apiKey, requestId) {
4070
const endpoint = 'https://api.scrapegraphai.com/v1/markdownify/' + requestId;

‎scrapegraph-js/src/searchScraper.js‎

Lines changed: 35 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -44,11 +44,44 @@ export async function searchScraper(apiKey, prompt, schema = null, userAgent = n
4444
}
4545

4646
/**
47-
* Retrieve the status or the result of searchScraper request. It also allows you to see the result of old requests.
47+
* Retrieve the status or result of a searchScraper request. This function allows you to check the progress
48+
* or retrieve results of both ongoing and completed search and extraction operations.
4849
*
4950
* @param {string} apiKey - Your ScrapeGraph AI API key
5051
* @param {string} requestId - The request ID associated with the output of a searchScraper request.
51-
* @returns {Promise<string>} Information related to the status or result of a scraping request.
52+
* @returns {Promise<Object>} A promise that resolves to an object containing:
53+
* - status: The current status of the request ('pending', 'completed', 'failed')
54+
* - result: The extracted data in JSON format when status is 'completed', including:
55+
* - extracted_data: The structured data extracted from search results
56+
* - source_urls: Array of URLs that were used as sources
57+
* - search_metadata: Information about the search operation
58+
* - error: Error message if the request failed (when status is 'failed')
59+
* - created_at: Timestamp of when the request was created
60+
* - completed_at: Timestamp of when the request was completed (if applicable)
61+
* @throws {Error} Throws an error if the HTTP request fails or if the API key is invalid
62+
*
63+
* @example
64+
* // Example usage:
65+
* const apiKey = 'your-api-key';
66+
* const requestId = 'previously-obtained-request-id';
67+
*
68+
* try {
69+
* const result = await getSearchScraperRequest(apiKey, requestId);
70+
* if (result.status === 'completed') {
71+
* console.log('Extracted data:', result.result.extracted_data);
72+
* console.log('Sources:', result.result.source_urls);
73+
* } else if (result.status === 'pending') {
74+
* console.log('Search and extraction still in progress');
75+
* } else {
76+
* console.log('Operation failed:', result.error);
77+
* }
78+
* } catch (error) {
79+
* console.error('Error fetching search results:', error);
80+
* }
81+
*
82+
* @note The search operation typically processes multiple web pages to gather comprehensive
83+
* information based on the original search query. The results are structured according to
84+
* the schema provided in the original searchScraper call, if any.
5285
*/
5386
export async function getSearchScraperRequest(apiKey, requestId) {
5487
const endpoint = 'https://api.scrapegraphai.com/v1/searchscraper/' + requestId;

‎scrapegraph-js/src/smartScraper.js‎

Lines changed: 25 additions & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -47,7 +47,31 @@ export async function smartScraper(apiKey, url, prompt, schema = null) {
4747
*
4848
* @param {string} apiKey - Your ScrapeGraph AI API key
4949
* @param {string} requestId - The request ID associated with the output of a smartScraper request.
50-
* @returns {Promise<string>} Information related to the status or result of a scraping request.
50+
* @returns {Promise<Object>} A promise that resolves to an object containing:
51+
* - status: The current status of the request ('pending', 'completed', 'failed')
52+
* - result: The extracted data in JSON format (when status is 'completed')
53+
* - error: Error message if the request failed (when status is 'failed')
54+
* - created_at: Timestamp of when the request was created
55+
* - completed_at: Timestamp of when the request was completed (if applicable)
56+
* @throws {Error} Throws an error if the HTTP request fails or if the API key is invalid
57+
*
58+
* @example
59+
* // Example usage:
60+
* const apiKey = 'your-api-key';
61+
* const requestId = 'previously-obtained-request-id';
62+
*
63+
* try {
64+
* const result = await getSmartScraperRequest(apiKey, requestId);
65+
* if (result.status === 'completed') {
66+
* console.log('Extracted data:', result.result);
67+
* } else if (result.status === 'pending') {
68+
* console.log('Request is still processing');
69+
* } else {
70+
* console.log('Request failed:', result.error);
71+
* }
72+
* } catch (error) {
73+
* console.error('Error fetching request:', error);
74+
* }
5175
*/
5276
export async function getSmartScraperRequest(apiKey, requestId) {
5377
const endpoint = 'https://api.scrapegraphai.com/v1/smartscraper/' + requestId;

‎scrapegraph-py/pyproject.toml‎

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -4,7 +4,7 @@ version = "1.8.0"
44
description = "ScrapeGraph Python SDK for API"
55
authors = [
66
{ name = "Marco Vinciguerra", email = "mvincig11@gmail.com" },
7-
{ name = "Marco Perini", email = "perinim.98@gmail.com" },
7+
{ name = "", email = "perinim.98@gmail.com" },
88
{ name = "Lorenzo Padoan", email = "lorenzo.padoan977@gmail.com" }
99
]
1010

0 commit comments

Comments
 (0)