Created
July 17, 2012 19:04
-
-
Save jsyeo/3131310 to your computer and use it in GitHub Desktop.
Collecting meta data of ODJ articles
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
#!/usr/bin/python -tt | |
import urllib | |
from lxml import etree | |
import simplejson | |
def main(): | |
'''main method: | |
code here''' | |
f = urllib.urlopen("http://ymiblogging.org/category/devotional/odj/") | |
body = f.read() | |
html = etree.HTML(body) | |
#xpath selection | |
titles = html.xpath("//h3/a/text()") | |
urls = [elem.attrib["href"] for elem in html.xpath("//h3/a")] | |
dates = html.xpath("//div[@class='post-meta']/strong/text()") | |
if len(titles) is len(urls) and len(urls) is len(dates): | |
odj_post = {} | |
json_file = open("feed.json", "w") | |
# for each title dump a json rep of the dict | |
for (i, title) in enumerate(titles): | |
odj_post["title"] = title | |
odj_post["url"] = urls[i] | |
odj_post["date"] = dates[i] | |
json_file.write(simplejson.dumps(odj_post)) | |
json_file.write("\n") | |
print "JSON output written to feed.json" | |
else: | |
print "HTML tag mis-match" | |
return | |
if __name__ == '__main__': | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment