thisismattmiller

import requests
import json


source_data = json.load(open('data.json'))



url = 'https://maps.googleapis.com/maps/api/geocode/json'

thisismattmiller

import requests
import shutil
import camelot.io as camelot
import os
from PyPDF2 import PdfFileReader, PdfFileWriter


for year in range(2011,2017):

	url = f'https://files.dep.state.pa.us/Waste/Recycling/RecyclingPortalFiles/Documents/{year}_Recycling_Report.pdf'	

thisismattmiller

import glob
from bs4 import BeautifulSoup
import json

all_files = list(glob.glob('html/*.html'))
all_data = []
for file_name in all_files:

	with open(file_name) as infile:

thisismattmiller

import glob
import json
urls = {}

for file in glob.glob('data_sogb/*'):

	with open(file) as inf:

thisismattmiller

import waybackpy

urls = [
"http://dmc.signourguestbook.com/?username=dmc&trail=25",
"http://dmc.signourguestbook.com/?username=dmc&trail=50",
"http://dmc.signourguestbook.com/?username=dmc&trail=75",
"http://dmc.signourguestbook.com/?username=dmc&trail=100",
"http://dmc.signourguestbook.com/?username=dmc&trail=125",
"http://dmc.signourguestbook.com/?username=dmc&trail=150",
"http://dmc.signourguestbook.com/?username=dmc&trail=175",

thisismattmiller

{
                        "id": "lc:RT:bf2:MIBluRayDVD:Instance",
                        "propertyTemplates": [
                            {
                                "mandatory": "false",
                                "propertyLabel": "Instance Of",
                                "propertyURI": "http://id.loc.gov/ontologies/bibframe/instanceOf",
                                "repeatable": "false",
                                "resourceTemplates": [],
                                "type": "resource",

thisismattmiller

{
  "russcarnahan.com": 16,
  "secure.actblue.com": 13,
  "secure.piryx.com": 6,
  "services.myngp.com": 5,
  "rickperry.org": 5,
  "secure.mydccc.org": 5,
  "markleyva.com": 4,
  "clyburnforcongress.com": 4,
  "johnsprattforcongress.com": 4,

thisismattmiller

<div><strong>imdb_id1</strong>: <a href="/movie/<%=imdb_id1%>"><%=imdb_id1%></a></div>
<div><strong>color1</strong>: <%=color1%></div>
<div><strong>director_name1</strong>: <%=director_name1%></div>
<div><strong>num_critic_for_reviews1</strong>: <%=num_critic_for_reviews1%></div>
<div><strong>duration1</strong>: <%=duration1%></div>
<div><strong>director_facebook_likes1</strong>: <%=director_facebook_likes1%></div>
<div><strong>actor_3_facebook_likes1</strong>: <%=actor_3_facebook_likes1%></div>
<div><strong>actor_2_name1</strong>: <%=actor_2_name1%></div>
<div><strong>actor_1_facebook_likes1</strong>: <%=actor_1_facebook_likes1%></div>
<div><strong>gross1</strong>: <%=gross1%></div>

thisismattmiller

import requests
import json

url = "http://data.carnegiehall.org/sparql/"

sparql = """
	#Find works by string in the title (case-insensitive)
	PREFIX dcterms: <http://purl.org/dc/terms/>
	PREFIX foaf: <http://xmlns.com/foaf/0.1/>
	PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>

thisismattmiller

import requests
from bs4 import BeautifulSoup
import json

all_item_urls = []

counter = 1


while counter <= 609: