Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Ajuste de São Paulo, SP para funcionar nos moldes atuais do QD (de 2017-06-01 em diante) #775

Closed
wants to merge 3 commits into from
Closed

Ajuste de São Paulo, SP para funcionar nos moldes atuais do QD (de 2017-06-01 em diante) #775

Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
d6d7ec5
sp_sao_paulo: remove explicit scraped_at
ayharano Nov 6, 2022
1eed4ab
sp_sao_paulo: replace locale use with a dict
ayharano Nov 6, 2022
9f5f0b3
sp_sao_paulo: use end_date parameter
ayharano Nov 7, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
31 changes: 24 additions & 7 deletions data_collection/gazette/spiders/sp/sp_sao_paulo.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,5 @@
import locale
import re
from datetime import date, datetime
from datetime import date

import scrapy
from dateutil.rrule import DAILY, rrule
Expand All @@ -9,6 +8,20 @@
from gazette.spiders.base import BaseGazetteSpider

RE_MAX_PAGE_NUM = re.compile(r"\d+ de (\d+)")
FULL_MONTH_NAME = {
1: "Janeiro",
2: "Fevereiro",
3: "Março",
4: "Abril",
5: "Maio",
6: "Junho",
7: "Julho",
8: "Agosto",
9: "Setembro",
10: "Outubro",
11: "Novembro",
12: "Dezembro",
}


class SpSaoPauloSpider(BaseGazetteSpider):
Expand All @@ -19,9 +32,7 @@ class SpSaoPauloSpider(BaseGazetteSpider):
start_date = date(2017, 6, 1)

def start_requests(self):
# Need to have the month's name in portuguese for the pdf url
locale.setlocale(locale.LC_TIME, "pt_BR.UTF-8")
for day in rrule(freq=DAILY, dtstart=self.start_date, until=date.today()):
for day in rrule(freq=DAILY, dtstart=self.start_date, until=self.end_date):
url = f"{self.BASE_URL}/nav_v6/header.asp?txtData={day.strftime('%d/%m/%Y')}&cad=1"
yield scrapy.Request(url, cb_kwargs=dict(day=day.date()))

Expand All @@ -39,7 +50,14 @@ def parse(self, response, day):
max_page = self.get_max_page(response)
if not max_page:
return
day_url = f"{self.BASE_URL}/doflash/prototipo/{day.strftime('%Y')}/{day.strftime('%B')}/{day.strftime('%d')}/cidade/pdf"
day_url = (
f"{self.BASE_URL}"
"/doflash/prototipo"
f"/{day.strftime('%Y')}"
f"/{FULL_MONTH_NAME[day.month]}"
f"/{day.strftime('%d')}"
"/cidade/pdf"
)
urls = [f"{day_url}/pg_{page:04}.pdf" for page in range(1, max_page + 1)]

yield Gazette(
Expand All @@ -48,5 +66,4 @@ def parse(self, response, day):
is_extra_edition=False,
territory_id=self.TERRITORY_ID,
power="executive",
scraped_at=datetime.utcnow(),
)
Loading