| import re | |
| import json | |
| ws_re = re.compile("\s+") | |
| line_num_re = re.compile("\s\d+\s{2,}", re.M) | |
| # first, pdftotext -layout <pdf> <text> | |
| with open("12-307_jnt1.txt", "r") as f: | |
| data = f.read() |
| import re | |
| def _extract_authors(byline): | |
| """ | |
| Takes one of our bylines returned from the Oxygen API, and | |
| tries to split it out into individual authors. Only works up | |
| to a triple byline. | |
| """ | |
| fallback_byline = re.compile("([\-\w.&; ]+)") | |
| single_byline = re.compile("By ([\-\w.&; ]+)") | |
| double_byline = re.compile("By ([\-\w.&; ]+) and ([\-\w.&; ]+)") |
| <link rel="stylesheet" href="http://osmbuildings.org/js/leaflet-0.5.1/leaflet.css"> | |
| <script src="http://osmbuildings.org/js/leaflet-0.5.1/leaflet.js"></script> | |
| <script src="http://osmbuildings.org/js/OSMBuildings-Leaflet.js"></script> | |
| <div id="map" style="width:100%; height:100%"></div> | |
| <script type="text/javascript"> | |
| var data = {"type": "FeatureCollection", "features": [{"geometry": {"type": "MultiPolygon", "coordinates": [[[[-118.22371230636624, 34.014919515466296], [-118.22370767851801, 34.01478070140346], [-118.22387331923136, 34.0147768774469], [-118.22387794727932, 34.014915663556124], [-118.22371230636624, 34.014919515466296]]]]}, "type": "Feature", "properties": {"ain": "5168023018", "height": 29.06}}, {"geometry": {"type": "MultiPolygon", "coordinates": [[[[-118.22353078318748, 34.01503069999131], [-118.22352664599238, 34.01493969843404], [-118.22363417872324, 34.0149363123561], [-118.22363831495248, 34.01502731391164], [-118.22353078318748, 34.01503069999131]]]]}, "type": "Feature", "properties": { |
| import mechanize | |
| from BeautifulSoup import BeautifulSoup | |
| def parse_table(html): | |
| """ | |
| Returns a list of lists. Each list is a row in the table. | |
| """ | |
| soup = BeautifulSoup(html) | |
| # The 9th table down the page is the one with all the info. | |
| table = soup.findAll('table')[9] |
| <meta name="viewport" content="width=device-width, initial-scale=1.0"> | |
| <link rel="stylesheet" href="http://cdn.leafletjs.com/leaflet-0.6.4/leaflet.css" /> | |
| <!--[if lte IE 8]> | |
| <link rel="stylesheet" href="http://cdn.leafletjs.com/leaflet-0.6.4/leaflet.ie.css" /> | |
| <![endif]--> | |
| <script src="http://cdn.leafletjs.com/leaflet-0.6.4/leaflet.js"></script> | |
| <script type="text/javascript"> | |
| geojson = {"type":"FeatureCollection","features":[{"type":"Feature","id":651,"properties":{"GEOID10":"06037600304","CT10":"600304","LABEL":"6003.04","X_Center":6472482.0,"Y_Center":1798989.0,"Shape_area":4798305.86046,"Shape_len":9662.240288860000874,"PNTCNT":15.0,"SumLev":"140","AreaName":"CensusTract6003.04","State":"06","AreaLand":"445759","AreaWatr":"0","TotPop":"3424","Wht":"50","Blk":"1330","Asn":"7","Hisp":"1986","Oth":"51","NAMELSAD10":"CensusTract6003.04","per_capita":0.0043808411,"PopInt":3424},"geometry":{"type":"Polygon","coordinates":[[[-118.291637000512452,33.939880999892225],[-118.291639000350102,33.939056000142166], |
Around 6:25 a.m. I was awakened by a jolt from slipping tectonic plates. The tremor didn't last very long, and as soon as my window stopped rattling my first thought was to check for an email.
Here it was:
L.A. Now: Ready for copyedit: Earthquake: 4.7 quake strikes near Westwood, California
This is a robopost from your friendly earthquake robot. Please copyedit & publish the
| import multiprocessing | |
| import subprocess | |
| from glob import glob | |
| import os | |
| fields = ["field1", "field2", "field3"] | |
| def work(fname): | |
| print "starting %s" % fname | |
| fname = os.path.abspath(fname) |
