sample_scrapper.py

import lxml
import requests

url = "https://www3.bcb.gov.br/sgspub/consultarvalores/consultarValoresSeries.do?method=consultarValores"
payload = {
    "optSelecionaSerie": "7460",
    "dataInicio": "31/01/1994",
    "dataFim": "01/12/2021",
    "selTipoArqDownload": "1",
    "chkPaginar": "on",
    "hdOidSeriesSelecionadas": "7460",
    "hdPaginar": "true",
    "bilServico": "[SGSFW2301]",
}
args = {"desired": "2021/12"}

def main():
    response = get_response_from_last_page()
    for row in get_valid_rows(response):
        month, value = parse_row(row)
        print(month, value)


def get_response_from_last_page():
    for i in range(1000):
        response = requests.post(url, payload)
        if search_desired_month(response):
            return response
    else:
        raise ValueError('Page not found for month "desired"')


def get_valid_rows(response):
    root = parse_html(response.content)
    table = root.find_by_css("#valoresSeries")
    for row in table.find_by_css("tbody tr"):
        if row.has_class("fundoPadraoAClaro3") or row.has_class("fundoPadraoAClaro2"):
            yield row


def parse_row(row):
    month, value = row.find_by_css("td")
    return parse_month(month), convert_to_float(value)


def search_desired_month(response):
    latest_month = get_latest_stored_month()
    return latest_month in response.content