diff --git a/notebooks/Firecrawl_Scraping.ipynb b/notebooks/Firecrawl_Scraping.ipynb index 2ac2da5..997772a 100644 --- a/notebooks/Firecrawl_Scraping.ipynb +++ b/notebooks/Firecrawl_Scraping.ipynb @@ -508,23 +508,22 @@ "for _, scraped_content in url_response.items():\n", " csv_data = scraped_content.get(\"csv_data\")\n", " scraped_results = scraped_content.get(\"scraped_data\")\n", - "\n", - " for scraped_site_dict in scraped_results:\n", - " for result in scraped_results:\n", - " markdown_content = result.get(\"markdown\")\n", - " title = result.get(\"metadata\").get(\"title\")\n", - " url = result.get(\"metadata\").get(\"sourceURL\")\n", - " documents.append(\n", - " Document(\n", - " text=markdown_content,\n", - " metadata={\n", - " \"title\": title,\n", - " \"url\": url,\n", - " \"description\": csv_data.get(\"Description\"),\n", - " \"category\": csv_data.get(\"Category\")\n", - " }\n", - " )\n", - " )\n" + "\n", + " for result in scraped_results:\n", + " markdown_content = result.get(\"markdown\")\n", + " title = result.get(\"metadata\").get(\"title\")\n", + " url = result.get(\"metadata\").get(\"sourceURL\")\n", + " documents.append(\n", + " Document(\n", + " text=markdown_content,\n", + " metadata={\n", + " \"title\": title,\n", + " \"url\": url,\n", + " \"description\": csv_data.get(\"Description\"),\n", + " \"category\": csv_data.get(\"Category\")\n", + " }\n", + " )\n", + " )\n" ] }, { @@ -736,4 +735,4 @@ }, "nbformat": 4, "nbformat_minor": 0 -} \ No newline at end of file +}