Created
February 16, 2011 15:45
-
-
Save billday/829585 to your computer and use it in GitHub Desktop.
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
| csvtopics = open("devzone.topics.csv", "rb") | |
| topicreader = csv.reader(csvtopics, dialect='excel') | |
| csvnumitems = open(devzonedir+"devzone.topics.items.csv", "wb") | |
| numitemswriter = csv.writer(csvnumitems, dialect='excel') | |
| for topic in topicreader: | |
| currenttopic = topic[0] | |
| topicfile = (currenttopic.replace(' ', '')).replace('.', 'dot') | |
| csvcurrenttopic = open(devzonedir+"devzone.analysis.topic."+topicfile+".csv", "wb") | |
| topicwriter = csv.DictWriter(csvcurrenttopic, fieldnames=['pubDate', 'articleOrBlog', 'title', 'link', 'hitCount'], restval='', extrasaction='ignore', dialect='excel') | |
| csvinput.seek(0) | |
| items = 0 | |
| for row in itemreader: | |
| if re.search(currenttopic,row['title']) or re.search(currenttopic,row['description']): | |
| topicwriter.writerow(row) | |
| items += 1 | |
| numitemswriter.writerow([currenttopic, items]) | |
| print topicfile, "topic contains", items, "items" | |
| csvcurrenttopic.close() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
This code excerpt is discussed in the article "Divining DevZone Insight from Filtered Feeds and Deep Pages: Part 2, The Analysis" at http://bit.ly/gXiAny