tjpb.py

# -*- coding: utf-8 -*-
from datetime import date
from urllib.parse import urlencode

import scrapy


class TjpbSpider(scrapy.Spider):
    name = "tjpb"
    allowed_domains = ["juris.tjpb.jus.br"]

    def start_requests(self):

        inicio = date(2013, 1, 1).strftime("%Y-%m-%d")
        fim = date(2018, 12, 31).strftime("%Y-%m-%d")
        classes = [
            "suspensão de segurança",
            "suspensão de liminar",
            "antecipação de tutela",
        ]

        params = {
            "q": "",
            "as_oq": "",
            "as_eq": "",
            "as_epq": "",
            "decisao": "Decisao",
            "output": "xml_no_dtd",
            "proxystylesheet": "tjpb_index",
            "oe": "UTF-8",
            "ie": "UTF-8",
            "ud": "1",
            "lr": "lang_pt",
            "getfields": "*",
            "requiredfields": "BASE:Decisao",
            "sort": "date:D:S:d1",
            "as_q": "inmeta:ORD_DATA_JULGAMENTO:daterange:{}..{}".format(inicio, fim),
            "ulang": "en",
            "access": "p",
            "entqr": "3",
            "entqrm": "0",
            "client": "tjpb_index",
            "filter": "0",
            "start": "0",
            "site": "jurisp_digitalizada",
        }

        for classe in classes:
            params["q"] = '"{}"'.format(classe)  # entre aspas
            url = "http://juris.tjpb.jus.br/search?{}".format(urlencode(params))
            yield scrapy.Request(url, callback=self.parse)

    def parse(self, response):
        for decisao in response.css(".result-item"):
            yield {
                "url": decisao.css("a::attr(href)").get().strip(),
                "processo": decisao.css("a::text").get().strip(),
                "relator": decisao.xpath(
                    ".//b[contains(text(),'Relator:')]/following-sibling::text()"
                )
                .get()
                .strip(),
                "julgamento": decisao.xpath(
                    ".//b[contains(text(),'Data de Julgamento:')]/"
                    "following-sibling::text()"
                )
                .get()
                .strip(),
                "ementa": decisao.css('.td_ementa::text').get().strip(),
            }

        next_page = response.css(".pagination-link:contains('>')::attr(href)").get()
        yield response.follow(next_page, callback=self.parse)