cosmoguard-bd/old/_old/echaFind.py

import requests
import urllib.parse
import re as standardre
import logging
import json
from bs4 import BeautifulSoup


# Settings per il logging
logging.basicConfig(
    format="{asctime} - {levelname} - {message}",
    style="{",
    datefmt="%Y-%m-%d %H:%M",
    filename="echa.log",
    encoding="utf-8",
    filemode="a",
    level=logging.INFO,
)

# Funzione inutile
def getCas(substance, ):
    results = {}
    req_0 = requests.get(
        "https://chem.echa.europa.eu/api-substance/v1/substance?pageIndex=1&pageSize=100&searchText="
        + urllib.parse.quote(substance)
    )
    req_0_json = req_0.json()
    try:
        rmlId = req_0_json["items"][0]["substanceIndex"]["rmlId"]
        rmlName = req_0_json["items"][0]["substanceIndex"]["rmlName"]
        rmlCas = req_0_json["items"][0]["substanceIndex"]["rmlCas"]

        results["rmlId"] = rmlId
        results["rmlName"] = rmlName
        results["rmlCas"] = rmlCas
    except:
        return False
    return results




# Funzione per cercare il dossier dato in input un CAS, una sostanza o un EN
def search_dossier(substance, input_type='rmlCas'):
    results = {}
    # Il dizionario che farò tornare alla fine 

    # Prima parte. Ottengo rmlID e rmlName
    # st.code('https://chem.echa.europa.eu/api-substance/v1/substance?pageIndex=1&pageSize=100&searchText='+substance)
    req_0 = requests.get(
        "https://chem.echa.europa.eu/api-substance/v1/substance?pageIndex=1&pageSize=100&searchText="
        + urllib.parse.quote(substance)
    )

    logging.info(f'echaFind.search_dossier(). searching "{substance}"')

    #'La prima cosa da fare è fare una ricerca con il nome della sostanza ma trasformata attraverso urllib'
    req_0_json = req_0.json()
    try:
       # Estraggo i campi che mi servono dalla response
        rmlId = req_0_json["items"][0]["substanceIndex"]["rmlId"]
        rmlName = req_0_json["items"][0]["substanceIndex"]["rmlName"]
        rmlCas = req_0_json["items"][0]["substanceIndex"]["rmlCas"]
        rmlEc = req_0_json["items"][0]["substanceIndex"]["rmlEc"]

        results['search_response'] = f"https://chem.echa.europa.eu/api-substance/v1/substance?pageIndex=1&pageSize=100&searchText={urllib.parse.quote(substance)}"
        results["rmlId"] = rmlId
        results["rmlName"] = rmlName
        results["rmlCas"] = rmlCas
        results["rmlEc"] = rmlEc

        logging.info(
            f"echaFind.search_dossier(). found substance on ECHA. rmlId: '{rmlId}', rmlName: '{rmlName}', rmlCas: '{rmlCas}'"
        )
    except:
        logging.info(
            f"echaFind.search_dossier(). could not find substance for '{substance}'"
        )
        return False
    
    # Update: in certi casi poteva verificarsi che inserendo un CAS si trovasse invece una sostanza con codice EN uguale al CAS in input.
    # Ora controllo che la sostanza trovata abbia effettivamente un CAS uguale a quello inserito in input.
    # è inoltre possibile cercare per rmlName (nome della sostanza) o EN (rmlEn): basta specificare in input_type per cosa si sta cercando
    if results[input_type] != substance:
        logging.error(f'echa.echaFind.search_dossier(): results[{input_type}] "{results[input_type]}is not equal to "{substance}". ')
        return f'search_error. results[{input_type}] ("{results[input_type]}") is not equal to "{substance}". Maybe you specified the wrong input_type. Check the results here: https://chem.echa.europa.eu/api-substance/v1/substance?pageIndex=1&pageSize=100&searchText={urllib.parse.quote(substance)}'

    # Seconda parte. Cerco sul sito ECHA dei dossiers creando un link con l'ID precedentemente ottenuto. 
    req_1_url = (
        "https://chem.echa.europa.eu/api-dossier-list/v1/dossier?pageIndex=1&pageSize=100&rmlId="
        + rmlId
        + "&registrationStatuses=Active"
    ) # Prima cerco negli active.

    req_1 = requests.get(req_1_url)
    req_1_json = req_1.json()

    # Se non esistono dossiers attivi cerco quelli inattivi
    if req_1_json["items"] == []:
        logging.info(
            f"echaFind.search_dossier(). could not find active dossier for '{substance}'. Proceeding to search in the unactive ones."
        )
        req_1_url = (
            "https://chem.echa.europa.eu/api-dossier-list/v1/dossier?pageIndex=1&pageSize=100&rmlId="
            + rmlId
            + "&registrationStatuses=Inactive"
        )
        req_1 = requests.get(req_1_url)
        req_1_json = req_1.json()
        if req_1_json["items"] == []:
            logging.info(
                f"echaFind.search_dossier(). could not find unactive dossiers for '{substance}'"
            ) # Non ho trovato nè dossiers inattivi che attivi
            return False
        else:
            logging.info(
                f"echaFind.search_dossier(). found unactive dossiers for '{rmlName}'"
            )
            results["dossierType"] = "Inactive"

    else:
        logging.info(
            f"echaFind.search_dossier(). found active dossiers for '{substance}'"
        )
        results["dossierType"] = "Active"

    # Queste erano le due robe che mi servivano
    assetExternalId = req_1_json["items"][0]["assetExternalId"]

    # UPDATE: Per ottenere la data dell'ultima modifica
    try:
        lastUpdateDate =  req_1_json["items"][0]["lastUpdatedDate"]
        datetime_object = datetime.fromisoformat(lastUpdateDate.replace('Z', '+00:00')) # Handle 'Z' if present, else it might break on older python versions
        lastUpdateDate = datetime_object.date().isoformat()
        results['lastUpdateDate'] = lastUpdateDate
    except:
        logging.error(f"echa.echaFind(). Could not find lastUpdateDate for the dossier")

    rootKey = req_1_json["items"][0]["rootKey"]

    # Terza parte. Ottengo assetExternalId
    # "Con l'assetExternalId è possibile arrivare alla pagina principale del dossier."
    # "Da questa pagina bisogna scrappare l'ID del riassunto tossicologico, :red[**SE ESISTE**]"
    results["index"] = (
        "https://chem.echa.europa.eu/html-pages/" + assetExternalId + "/index.html"
    )
    results["index_js"] = (
        f"https://chem.echa.europa.eu/{rmlId}/dossier-view/{assetExternalId}"
    )

    req_2 = requests.get(
        "https://chem.echa.europa.eu/html-pages/" + assetExternalId + "/index.html"
    )
    index = BeautifulSoup(req_2.text, "html.parser")
    index.prettify()

    # Quarta parte. Ottengo l'ID del riassunto tossicologico dall'index.html
    # "In tutto quell'HTML ci interessa solo un div. BeautifulSoup ha problemi se ci sono troppi div innestati. Quindi uso una combinazione di quello e di Regex"

    div = index.find_all("div", id=["id_7_Toxicologicalinformation"])
    str_div = str(div)
    str_div = str_div.split("</div>")[0]

    uic_found = False
    if type(standardre.search('href="([^"]+)"', str_div)).__name__ == "NoneType":
        # Un regex per trovare l'href che mi serve
        logging.info(
            f"echaFind.search_dossier(). Could not find 'id_7_Toxicologicalinformation' in the body"
        )
    else:
        UIC = standardre.search('href="([^"]+)"', str_div).group(1)
        uic_found = True

    # Per l'acute toxicity
    acute_toxicity_found = False
    div_acute_toxicity = index.find_all("div", id=["id_72_AcuteToxicity"])
    if div_acute_toxicity:
        for div in div_acute_toxicity:
            try:
                a = div.find_all("a", href=True)[0]
                acute_toxicity_id = standardre.search('href="([^"]+)"', str(a)).group(1)
                acute_toxicity_found = True
            except:
                logging.info(
                    f"echaFind.search_dossier(). No acute_toxicity_id found from index for {substance}"
                )

    # Per il repeated dose
    repeated_dose_found = False
    div_repeated_dose = index.find_all("div", id=["id_75_Repeateddosetoxicity"])
    if div_repeated_dose:
        for div in div_repeated_dose:
            try:
                a = div.find_all("a", href=True)[0]
                repeated_dose_id = standardre.search('href="([^"]+)"', str(a)).group(1)
                repeated_dose_found = True
            except:
                logging.info(
                    f"echaFind.search_dossier(). No repeated_dose_id found from index for {substance}"
                )

    # Quinta parte. Recupero l'html del dossier tossicologico e faccio ritornare il content

    if acute_toxicity_found:
        acute_toxicity_link = (
            "https://chem.echa.europa.eu/html-pages/"
            + assetExternalId
            + "/documents/"
            + acute_toxicity_id
            + ".html"
        )
        results["AcuteToxicity"] = acute_toxicity_link
        results["AcuteToxicity_js"] = (
            f"https://chem.echa.europa.eu/{rmlId}/dossier-view/{assetExternalId}/{acute_toxicity_id}"
        )

    if uic_found:
        # UIC è l'id del toxsummary
        final_url = (
            "https://chem.echa.europa.eu/html-pages/"
            + assetExternalId
            + "/documents/"
            + UIC
            + ".html"
        )
        results["ToxSummary"] = final_url
        results["ToxSummary_js"] = (
            f"https://chem.echa.europa.eu/{rmlId}/dossier-view/{assetExternalId}/{UIC}"
        )

    if repeated_dose_found:
        results["RepeatedDose"] = (
            "https://chem.echa.europa.eu/html-pages/"
            + assetExternalId
            + "/documents/"
            + repeated_dose_id
            + ".html"
        )
        results["RepeatedDose_js"] = (
            f"https://chem.echa.europa.eu/{rmlId}/dossier-view/{assetExternalId}/{repeated_dose_id}"
        )

    json_formatted_str = json.dumps(results)
    logging.info(f"echaFind.search_dossier() OK. output: {json_formatted_str}")
    return results