| addEventListener("fetch", (event) => { | |
| event.respondWith( | |
| handleRequest(event).catch( | |
| (err) => new Response(err.stack, { status: 500 }) | |
| ) | |
| ); | |
| }); | |
| from selenium import webdriver | |
| from selenium.webdriver.support.ui import WebDriverWait | |
| from selenium.webdriver.support import expected_conditions as EC | |
| from selenium.webdriver.common.by import By | |
| with webdriver.Chrome() as driver: | |
| # load the page | |
| driver.get("https://dapps.36thdistrictcourt.org/ROAWEBINQ/Default.aspx") |
should be able to scrape changing bookingNumber in the data payload.
For Justin Walker:
curl 'https://inmatelocator.ccsheriff.org/InmateLocator/Details'
-H 'User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10.13; rv:75.0) Gecko/20100101 Firefox/75.0'
-H 'Accept: text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8'
-H 'Accept-Language: en-US,en;q=0.5'
--compressed
| import psycopg2 | |
| import io | |
| import csv | |
| import itertools | |
| class Readable(object): | |
| def __init__(self, iterator): | |
| self.output = io.StringIO() |
| def batched_result_generator(cur): | |
| offset = 0 | |
| batchsize = 100 | |
| exhausted = False | |
| while not exhausted: | |
| results = cur.execute('select ... from offset = ? limit = ?', (offset, batchsize)).fetchall() | |
| if len(results) < batchsize: | |
| exhausted = True | |
| for row in results: | |
| yield row |
| ward | community | proportion_of_ward_in_community_area | |
|---|---|---|---|
| 1 | WEST TOWN | 0.583178464274206 | |
| 1 | LOGAN SQUARE | 0.392380054759725 | |
| 1 | HUMBOLDT PARK | 5.05596447686876e-05 | |
| 1 | NORTH CENTER | 0.00942203809405585 | |
| 1 | LINCOLN PARK | 0.0149688832272447 | |
| 10 | HEGEWISCH | 0.265895481584491 | |
| 10 | SOUTH CHICAGO | 0.0768757437832051 | |
| 10 | RIVERDALE | 3.43949272079429e-09 | |
| 10 | EAST SIDE | 0.151634348793321 |
| library(tidyverse) | |
| library(lubridate) # we'll use this for some date processing | |
| # Read in the data | |
| intake <- read.csv("Intake.csv") | |
| initiation <- read.csv("Initiation.csv") | |
| # Turn RECEIVED_DATE from strings to date objects | |
| intake <- intake %>% | |
| mutate(RECEIVED_DATE = as.Date(RECEIVED_DATE, '%m/%d/%Y')) |
| # This software is a modified version of the bisect module found | |
| # https://github.com/choderalab/thresholds/blob/master/thresholds/bisect.py | |
| # | |
| # MIT License | |
| # Copyright (c) 2018 Chodera lab // Memorial Sloan Kettering Cancer | |
| # Center | |
| # Permission is hereby granted, free of charge, to any person | |
| # obtaining a copy of this software and associated documentation files |