gEDA-user: script to get part info from digikey

[Josh Jordan <outerspaceman81@xxxxxxxxx>]

   This script takes a column of digikey part numbers and retrieves mfg,
   mfg#, and price breakdowns from the digikey website.
   I might write some more scripts like this to get part info from other
   websites like mouser and farnell.

#Input: file named digikey.csv that has 1 column of digikey part numbers
#		this can be copy/pasted from gattrib if digikey# is stored in symbols
#Output: file named digikeyinfo.csv columns digikey#, mfg, mfg#, and quantity-price pairs
#		rows will probably have different amount of columns due to different quantity-prices
#by Josh Jordan josh.outerspace@xxxxxxxxx 

import sys
import urllib2
import re
import string

ifile = open("digikey.csv", "r")
ofile = open("digikeyinfo.csv", "w")
#wpage = open("test.html", "w") #save html page if a regex doesnt work
dks = "http://search.digikey.com/scripts/DkSearch/dksus.dll?Detail&name=";
for line in ifile:
	#skipping certain csv lines and adding -ND to any digikey# without it
	part = line.rstrip()
	if part.startswith("digikey"):
		ofile.write("digikey,mfg,mfgnum\n")
		continue
	if part.startswith("unknown"):
		ofile.write("unknown,unknown\n")
		continue
	if not part.endswith("-ND"):
		part += "-ND"
	#this is the url to the page of digikey part information
	url = dks+part
	page = urllib2.urlopen(url)
	pstring = page.read()
	#try to get mfg part number
	regex = '<tr><th align=right>Manufacturer Part Number</th><td>(.*?)</td></tr>'
	mat = re.search(regex, pstring)
	try:
		mfgnum = mat.group(1)
	except:
		mfgnum = "NF"
	#try to get mfg name
	regex = '<tr><th align=right>Manufacturer</th><td><a href="(?:.*?)">(.*?)(?:<.*?></a>|</a>)</td></tr>'
	mat = re.search(regex, pstring)
	try:
		mfg = mat.group(1)
	except:
		mfg = "NF"
	#add price breakdowns in breakdown/price pairs
	breakdownprice = ""
	price_s = "<tr><th>Price Break</th><th>Unit Price</th><th>Extended Price</th></tr>"
	regex = '<tr><td align=center>(.*?)</td><td align=right>(.*?)</td><td align=right>(?:.*?)</td></tr>'
	plines = re.split("\n+", pstring)
	for i, line in enumerate(plines):
		if price_s == line:
			break
	plines = plines[i+1:]
	prevpb = 0
	for line in plines:
		mat = re.match(regex, line)
		try:
			pbreak = mat.group(1).replace(",", "")
			price = mat.group(2)
			if int(pbreak) < prevpb:
				print "pbreak wrong- " + int(pbreak.replace(",", "")) + " >= " + prevpb
				break
			prevpb = int(pbreak)
			breakdownprice += ", " + pbreak +", "+ price
		except:
			break
	output = part + ", " + mfg + ", " + mfgnum + breakdownprice+'\n'
	print output
	ofile.write(output)
ofile.flush()


_______________________________________________
geda-user mailing list
geda-user@xxxxxxxxxxxxxx
http://www.seul.org/cgi-bin/mailman/listinfo/geda-user