Merge pull request #323 from VinciGit00/refactoring-pdf_scraper

Refactoring pdf scraper and json scrape

Author: PeriniM

examples/anthropic/csv_scraper_graph_multi_haiku.py

@@ -0,0 +1,55 @@
+"""
+Basic example of scraping pipeline using CSVScraperMultiGraph from CSV documents
+"""
+
+import os
+from dotenv import load_dotenv
+import pandas as pd
+from scrapegraphai.graphs import CSVScraperMultiGraph
+from scrapegraphai.utils import convert_to_csv, convert_to_json, prettify_exec_info
+
+load_dotenv()
+# ************************************************
+# Read the CSV file
+# ************************************************
+
+FILE_NAME = "inputs/username.csv"
+curr_dir = os.path.dirname(os.path.realpath(__file__))
+file_path = os.path.join(curr_dir, FILE_NAME)
+
+text = pd.read_csv(file_path)
+
+# ************************************************
+# Define the configuration for the graph
+# ************************************************
+
+graph_config = {
+    "llm": {
+        "api_key": os.getenv("ANTHROPIC_API_KEY"),
+        "model": "claude-3-haiku-20240307",
+        "max_tokens": 4000},
+}
+
+# ************************************************
+# Create the CSVScraperMultiGraph instance and run it
+# ************************************************
+
+csv_scraper_graph = CSVScraperMultiGraph(
+    prompt="List me all the last names",
+    source=[str(text), str(text)],
+    config=graph_config
+)
+
+result = csv_scraper_graph.run()
+print(result)
+
+# ************************************************
+# Get graph execution info
+# ************************************************
+
+graph_exec_info = csv_scraper_graph.get_execution_info()
+print(prettify_exec_info(graph_exec_info))
+
+# Save to json or csv
+convert_to_csv(result, "result")
+convert_to_json(result, "result")

examples/anthropic/json_scraper_multi_haiku.py

@@ -0,0 +1,36 @@
+"""
+Module for showing how JSONScraperMultiGraph multi works
+"""
+import os
+import json
+from dotenv import load_dotenv
+from scrapegraphai.graphs import JSONScraperMultiGraph
+
+load_dotenv()
+
+graph_config = {
+    "llm": {
+        "api_key": os.getenv("ANTHROPIC_API_KEY"),
+        "model": "claude-3-haiku-20240307",
+        "max_tokens": 4000
+        },
+}
+
+FILE_NAME = "inputs/example.json"
+curr_dir = os.path.dirname(os.path.realpath(__file__))
+file_path = os.path.join(curr_dir, FILE_NAME)
+
+with open(file_path, 'r', encoding="utf-8") as file:
+    text = file.read()
+
+sources = [text, text]
+
+multiple_search_graph = JSONScraperMultiGraph(
+    prompt= "List me all the authors, title and genres of the books",
+    source= sources,
+    schema=None,
+    config=graph_config
+)
+
+result = multiple_search_graph.run()
+print(json.dumps(result, indent=4))

examples/anthropic/pdf_scraper_graph_haiku.py

@@ -1,10 +1,12 @@
+""" 
+Module for showing how PDFScraper multi works
+"""
 import os, json
 from dotenv import load_dotenv
 from scrapegraphai.graphs import PDFScraperGraph
 
 load_dotenv()
 
-
 # ************************************************
 # Define the configuration for the graph
 # ************************************************

examples/anthropic/pdf_scraper_multi_haiku.py

@@ -0,0 +1,72 @@
+"""
+Module for showing how PDFScraper multi works
+"""
+import os
+import json
+from dotenv import load_dotenv
+from scrapegraphai.graphs import PdfScraperMultiGraph
+
+load_dotenv()
+
+graph_config = {
+    "llm": {
+        "api_key": os.getenv("ANTHROPIC_API_KEY"),
+        "model": "claude-3-haiku-20240307",
+        "max_tokens": 4000
+        },
+}
+
+# ***************
+# Covert to list
+# ***************
+
+sources = [
+    "This paper provides evidence from a natural experiment on the relationship between positive affect and productivity. We link highly detailed administrative data on the behaviors and performance of all telesales workers at a large telecommunications company with survey reports of employee happiness that we collected on a weekly basis. We use variation in worker mood arising from visual exposure to weather—the interaction between call center architecture and outdoor weather conditions—in order to provide a quasi-experimental test of the effect of happiness on productivity. We find evidence of a positive impact on sales performance, which is driven by changes in labor productivity – largely through workers converting more calls into sales, and to a lesser extent by making more calls per hour and adhering more closely to their schedule. We find no evidence in our setting of effects on measures of high-frequency labor supply such as attendance and break-taking.",
+    "This paper provides evidence from a natural experiment on the relationship between positive affect and productivity. We link highly detailed administrative data on the behaviors and performance of all telesales workers at a large telecommunications company with survey reports of employee happiness that we collected on a weekly basis. We use variation in worker mood arising from visual exposure to weather—the interaction between call center architecture and outdoor weather conditions—in order to provide a quasi-experimental test of the effect of happiness on productivity. We find evidence of a positive impact on sales performance, which is driven by changes in labor productivity – largely through workers converting more calls into sales, and to a lesser extent by making more calls per hour and adhering more closely to their schedule. We find no evidence in our setting of effects on measures of high-frequency labor supply such as attendance and break-taking.",
+    "This paper provides evidence from a natural experiment on the relationship between positive affect and productivity. We link highly detailed administrative data on the behaviors and performance of all telesales workers at a large telecommunications company with survey reports of employee happiness that we collected on a weekly basis. We use variation in worker mood arising from visual exposure to weather—the interaction between call center architecture and outdoor weather conditions—in order to provide a quasi-experimental test of the effect of happiness on productivity. We find evidence of a positive impact on sales performance, which is driven by changes in labor productivity – largely through workers converting more calls into sales, and to a lesser extent by making more calls per hour and adhering more closely to their schedule. We find no evidence in our setting of effects on measures of high-frequency labor supply such as attendance and break-taking.",
+    "This paper provides evidence from a natural experiment on the relationship between positive affect and productivity. We link highly detailed administrative data on the behaviors and performance of all telesales workers at a large telecommunications company with survey reports of employee happiness that we collected on a weekly basis. We use variation in worker mood arising from visual exposure to weather—the interaction between call center architecture and outdoor weather conditions—in order to provide a quasi-experimental test of the effect of happiness on productivity. We find evidence of a positive impact on sales performance, which is driven by changes in labor productivity – largely through workers converting more calls into sales, and to a lesser extent by making more calls per hour and adhering more closely to their schedule. We find no evidence in our setting of effects on measures of high-frequency labor supply such as attendance and break-taking.",
+]
+
+prompt = """
+You are an expert in reviewing academic manuscripts. Please analyze the abstracts provided from an academic journal article to extract and clearly identify the following elements:
+
+Independent Variable (IV): The variable that is manipulated or considered as the primary cause affecting other variables.
+Dependent Variable (DV): The variable that is measured or observed, which is expected to change as a result of variations in the Independent Variable.
+Exogenous Shock: Identify any external or unexpected events used in the study that serve as a natural experiment or provide a unique setting for observing the effects on the IV and DV.
+Response Format: For each abstract, present your response in the following structured format:
+
+Independent Variable (IV):
+Dependent Variable (DV):
+Exogenous Shock:
+
+Example Queries and Responses:
+
+Query: This paper provides evidence from a natural experiment on the relationship between positive affect and productivity. We link highly detailed administrative data on the behaviors and performance of all telesales workers at a large telecommunications company with survey reports of employee happiness that we collected on a weekly basis. We use variation in worker mood arising from visual exposure to weather the interaction between call center architecture and outdoor weather conditions in order to provide a quasi-experimental test of the effect of happiness on productivity. We find evidence of a positive impact on sales performance, which is driven by changes in labor productivity largely through workers converting more calls into sales, and to a lesser extent by making more calls per hour and adhering more closely to their schedule. We find no evidence in our setting of effects on measures of high-frequency labor supply such as attendance and break-taking.
+
+Response:
+
+Independent Variable (IV): Employee happiness.
+Dependent Variable (DV): Overall firm productivity.
+Exogenous Shock: Sudden company-wide increase in bonus payments.
+
+Query: The diffusion of social media coincided with a worsening of mental health conditions among adolescents and young adults in the United States, giving rise to speculation that social media might be detrimental to mental health. In this paper, we provide quasi-experimental estimates of the impact of social media on mental health by leveraging a unique natural experiment: the staggered introduction of Facebook across U.S. colleges. Our analysis couples data on student mental health around the years of Facebook's expansion with a generalized difference-in-differences empirical strategy. We find that the roll-out of Facebook at a college increased symptoms of poor mental health, especially depression. We also find that, among students predicted to be most susceptible to mental illness, the introduction of Facebook led to increased utilization of mental healthcare services. Lastly, we find that, after the introduction of Facebook, students were more likely to report experiencing impairments to academic performance resulting from poor mental health. Additional evidence on mechanisms suggests that the results are due to Facebook fostering unfavorable social comparisons.
+
+Response:
+
+Independent Variable (IV): Exposure to social media.
+Dependent Variable (DV): Mental health outcomes.
+Exogenous Shock: staggered introduction of Facebook across U.S. colleges.
+"""
+# *******************************************************
+# Create the SmartScraperMultiGraph instance and run it
+# *******************************************************
+
+multiple_search_graph = PdfScraperMultiGraph(
+    prompt=prompt,
+    source= sources,
+    schema=None,
+    config=graph_config
+)
+
+result = multiple_search_graph.run()
+print(json.dumps(result, indent=4))

examples/anthropic/xml_scraper_graph_multi_haiku.py

@@ -0,0 +1,55 @@
+"""
+Basic example of scraping pipeline using XMLScraperMultiGraph from XML documents
+"""
+
+import os
+from dotenv import load_dotenv
+from scrapegraphai.graphs import XMLScraperMultiGraph
+from scrapegraphai.utils import convert_to_csv, convert_to_json, prettify_exec_info
+load_dotenv()
+
+# ************************************************
+# Read the XML file
+# ************************************************
+
+FILE_NAME = "inputs/books.xml"
+curr_dir = os.path.dirname(os.path.realpath(__file__))
+file_path = os.path.join(curr_dir, FILE_NAME)
+
+with open(file_path, 'r', encoding="utf-8") as file:
+    text = file.read()
+
+# ************************************************
+# Define the configuration for the graph
+# ************************************************
+
+graph_config = {
+    "llm": {
+        "api_key": os.getenv("ANTHROPIC_API_KEY"),
+        "model": "claude-3-haiku-20240307",
+        "max_tokens": 4000},
+}
+
+# ************************************************
+# Create the XMLScraperMultiGraph instance and run it
+# ************************************************
+
+xml_scraper_graph = XMLScraperMultiGraph(
+    prompt="List me all the authors, title and genres of the books",
+    source=[text, text],  # Pass the content of the file, not the file object
+    config=graph_config
+)
+
+result = xml_scraper_graph.run()
+print(result)
+
+# ************************************************
+# Get graph execution info
+# ************************************************
+
+graph_exec_info = xml_scraper_graph.get_execution_info()
+print(prettify_exec_info(graph_exec_info))
+
+# Save to json or csv
+convert_to_csv(result, "result")
+convert_to_json(result, "result")

examples/bedrock/csv_scraper_graph_multi_bedrock.py

@@ -0,0 +1,59 @@
+"""
+Basic example of scraping pipeline using CSVScraperMultiGraph from CSV documents
+"""
+
+import os
+from dotenv import load_dotenv
+import pandas as pd
+from scrapegraphai.graphs import CSVScraperMultiGraph
+from scrapegraphai.utils import convert_to_csv, convert_to_json, prettify_exec_info
+
+load_dotenv()
+# ************************************************
+# Read the CSV file
+# ************************************************
+
+FILE_NAME = "inputs/username.csv"
+curr_dir = os.path.dirname(os.path.realpath(__file__))
+file_path = os.path.join(curr_dir, FILE_NAME)
+
+text = pd.read_csv(file_path)
+
+# ************************************************
+# Define the configuration for the graph
+# ************************************************
+
+graph_config = {
+    "llm": {
+        "client": "client_name",
+        "model": "bedrock/anthropic.claude-3-sonnet-20240229-v1:0",
+        "temperature": 0.0
+    },
+    "embeddings": {
+        "model": "bedrock/cohere.embed-multilingual-v3"
+    }
+}
+
+# ************************************************
+# Create the CSVScraperMultiGraph instance and run it
+# ************************************************
+
+csv_scraper_graph = CSVScraperMultiGraph(
+    prompt="List me all the last names",
+    source=[str(text), str(text)],
+    config=graph_config
+)
+
+result = csv_scraper_graph.run()
+print(result)
+
+# ************************************************
+# Get graph execution info
+# ************************************************
+
+graph_exec_info = csv_scraper_graph.get_execution_info()
+print(prettify_exec_info(graph_exec_info))
+
+# Save to json or csv
+convert_to_csv(result, "result")
+convert_to_json(result, "result")

examples/bedrock/xml_scraper_graph_multi_bedrock.py

@@ -0,0 +1,59 @@
+"""
+Basic example of scraping pipeline using XMLScraperMultiGraph from XML documents
+"""
+
+import os
+from dotenv import load_dotenv
+from scrapegraphai.graphs import XMLScraperMultiGraph
+from scrapegraphai.utils import convert_to_csv, convert_to_json, prettify_exec_info
+load_dotenv()
+
+# ************************************************
+# Read the XML file
+# ************************************************
+
+FILE_NAME = "inputs/books.xml"
+curr_dir = os.path.dirname(os.path.realpath(__file__))
+file_path = os.path.join(curr_dir, FILE_NAME)
+
+with open(file_path, 'r', encoding="utf-8") as file:
+    text = file.read()
+
+# ************************************************
+# Define the configuration for the graph
+# ************************************************
+
+graph_config = {
+    "llm": {
+        "client": "client_name",
+        "model": "bedrock/anthropic.claude-3-sonnet-20240229-v1:0",
+        "temperature": 0.0
+    },
+    "embeddings": {
+        "model": "bedrock/cohere.embed-multilingual-v3"
+    }
+}
+
+# ************************************************
+# Create the XMLScraperMultiGraph instance and run it
+# ************************************************
+
+xml_scraper_graph = XMLScraperMultiGraph(
+    prompt="List me all the authors, title and genres of the books",
+    source=[text, text],  # Pass the content of the file, not the file object
+    config=graph_config
+)
+
+result = xml_scraper_graph.run()
+print(result)
+
+# ************************************************
+# Get graph execution info
+# ************************************************
+
+graph_exec_info = xml_scraper_graph.get_execution_info()
+print(prettify_exec_info(graph_exec_info))
+
+# Save to json or csv
+convert_to_csv(result, "result")
+convert_to_json(result, "result")