Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
blablupcom
committed
Dec 9, 2015
1 parent
c247efb
commit d8acf88
Showing
1 changed file
with
84 additions
and
47 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -1,97 +1,134 @@ | ||
# -*- coding: utf-8 -*- | ||
|
||
#### IMPORTS 1.0 | ||
|
||
import os | ||
import re | ||
import requests | ||
import scraperwiki | ||
import urllib2 | ||
from datetime import datetime | ||
from bs4 import BeautifulSoup | ||
from dateutil.parser import parse | ||
|
||
# Set up variables | ||
entity_id = "E1301_DBC_gov" | ||
url = "http://www.darlington.gov.uk/your-council/council-information/financial-information/spending-data/" | ||
errors = 0 | ||
# Set up functions | ||
#### FUNCTIONS 1.0 | ||
|
||
def validateFilename(filename): | ||
filenameregex = '^[a-zA-Z0-9]+_[a-zA-Z0-9]+_[a-zA-Z0-9]+_[0-9][0-9][0-9][0-9]_[0-9][0-9]$' | ||
dateregex = '[0-9][0-9][0-9][0-9]_[0-9][0-9]' | ||
filenameregex = '^[a-zA-Z0-9]+_[a-zA-Z0-9]+_[a-zA-Z0-9]+_[0-9][0-9][0-9][0-9]_[0-9QY][0-9]$' | ||
dateregex = '[0-9][0-9][0-9][0-9]_[0-9QY][0-9]' | ||
validName = (re.search(filenameregex, filename) != None) | ||
found = re.search(dateregex, filename) | ||
if not found: | ||
return False | ||
date = found.group(0) | ||
year, month = int(date[:4]), int(date[5:7]) | ||
now = datetime.now() | ||
validYear = (2000 <= year <= now.year) | ||
validMonth = (1 <= month <= 12) | ||
year, month = date[:4], date[5:7] | ||
validYear = (2000 <= int(year) <= now.year) | ||
if 'Q' in date: | ||
validMonth = (month in ['Q0', 'Q1', 'Q2', 'Q3', 'Q4']) | ||
elif 'Y' in date: | ||
validMonth = (month in ['Y1']) | ||
else: | ||
try: | ||
validMonth = datetime.strptime(date, "%Y_%m") < now | ||
except: | ||
return False | ||
if all([validName, validYear, validMonth]): | ||
return True | ||
|
||
|
||
def validateURL(url): | ||
try: | ||
r = requests.get(url, allow_redirects=True, timeout=20) | ||
r = urllib2.urlopen(url) | ||
count = 1 | ||
while r.status_code == 500 and count < 4: | ||
while r.getcode() == 500 and count < 4: | ||
print ("Attempt {0} - Status code: {1}. Retrying.".format(count, r.status_code)) | ||
count += 1 | ||
r = requests.get(url, allow_redirects=True, timeout=20) | ||
r = urllib2.urlopen(url) | ||
sourceFilename = r.headers.get('Content-Disposition') | ||
|
||
if sourceFilename: | ||
ext = os.path.splitext(sourceFilename)[1].replace('"', '').replace(';', '').replace(' ', '') | ||
else: | ||
ext = os.path.splitext(url)[1] | ||
validURL = r.status_code == 200 | ||
validFiletype = ext in ['.csv', '.xls', '.xlsx'] | ||
validURL = r.getcode() == 200 | ||
validFiletype = ext.lower() in ['.csv', '.xls', '.xlsx'] | ||
return validURL, validFiletype | ||
except: | ||
raise | ||
def convert_mth_strings ( mth_string ): | ||
print ("Error validating URL.") | ||
return False, False | ||
|
||
|
||
def validate(filename, file_url): | ||
validFilename = validateFilename(filename) | ||
validURL, validFiletype = validateURL(file_url) | ||
if not validFilename: | ||
print filename, "*Error: Invalid filename*" | ||
print file_url | ||
return False | ||
if not validURL: | ||
print filename, "*Error: Invalid URL*" | ||
print file_url | ||
return False | ||
if not validFiletype: | ||
print filename, "*Error: Invalid filetype*" | ||
print file_url | ||
return False | ||
return True | ||
|
||
|
||
def convert_mth_strings ( mth_string ): | ||
month_numbers = {'JAN': '01', 'FEB': '02', 'MAR':'03', 'APR':'04', 'MAY':'05', 'JUN':'06', 'JUL':'07', 'AUG':'08', 'SEP':'09','OCT':'10','NOV':'11','DEC':'12' } | ||
#loop through the months in our dictionary | ||
for k, v in month_numbers.items(): | ||
#then replace the word with the number | ||
|
||
mth_string = mth_string.replace(k, v) | ||
return mth_string | ||
# pull down the content from the webpage | ||
|
||
#### VARIABLES 1.0 | ||
|
||
entity_id = "E1301_DBC_gov" | ||
url = "http://www.darlington.gov.uk/your-council/council-information/financial-information/spending-data/" | ||
errors = 0 | ||
data = [] | ||
|
||
#### READ HTML 1.0 | ||
|
||
html = urllib2.urlopen(url) | ||
soup = BeautifulSoup(html, 'lxml') | ||
# find all entries with the required class | ||
|
||
|
||
#### SCRAPE DATA | ||
|
||
block = soup.find('section', attrs = {'id':'mainContent'}) | ||
links = block.findAll('a', href=True) | ||
for link in links: | ||
csvFile = link.text.strip() | ||
if 'CSV' in csvFile: | ||
if '.csv' in link['href']: | ||
Mth = csvFile.split(' ')[0].strip()[:3] | ||
csvYr = csvFile.split(' ') | ||
if len(csvYr) == 4: | ||
csvYr = csvYr[-1].strip()[:5].strip() | ||
else: | ||
csvYr = csvYr[1].strip()[:5].strip() | ||
url = 'http://www.darlington.gov.uk' + link['href'] | ||
csvMth = convert_mth_strings(Mth.upper()) | ||
filename = entity_id + "_" + csvYr + "_" + csvMth | ||
todays_date = str(datetime.now()) | ||
file_url = 'http://www.darlington.gov.uk' + link['href'] | ||
validFilename = validateFilename(filename) | ||
validURL, validFiletype = validateURL(file_url) | ||
if not validFilename: | ||
print filename, "*Error: Invalid filename*" | ||
print file_url | ||
errors += 1 | ||
continue | ||
if not validURL: | ||
print filename, "*Error: Invalid URL*" | ||
print file_url | ||
errors += 1 | ||
continue | ||
if not validFiletype: | ||
print filename, "*Error: Invalid filetype*" | ||
print file_url | ||
errors += 1 | ||
continue | ||
data.append([csvYr, csvMth, url]) | ||
|
||
#### STORE DATA 1.0 | ||
|
||
for row in data: | ||
csvYr, csvMth, url = row | ||
filename = entity_id + "_" + csvYr + "_" + csvMth | ||
todays_date = str(datetime.now()) | ||
file_url = url.strip() | ||
|
||
valid = validate(filename, file_url) | ||
|
||
if valid == True: | ||
scraperwiki.sqlite.save(unique_keys=['l'], data={"l": file_url, "f": filename, "d": todays_date }) | ||
print filename | ||
if errors > 0: | ||
raise Exception("%d errors occurred during scrape." % errors) | ||
else: | ||
errors += 1 | ||
|
||
if errors > 0: | ||
raise Exception("%d errors occurred during scrape." % errors) | ||
|
||
|
||
#### EOF |