Last active
March 3, 2017 05:59
-
-
Save intrd/2c19ee22c3bd98ed07612c6ad3adc25d to your computer and use it in GitHub Desktop.
Wikipedia parser (birth data extractor)
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
## Wikipedia parser (birth data extractor) | |
# @author intrd - http://dann.com.br/ (based on @JBernardo's suggestion http://stackoverflow.com/a/12250675) | |
# @license Creative Commons Attribution-ShareAlike 4.0 International License - http://creativecommons.org/licenses/by-sa/4.0/ | |
import re, requests | |
from bs4 import BeautifulSoup | |
def wikiGet(name): | |
url = 'http://en.wikipedia.org/w/api.php?action=query&prop=revisions&rvprop=content&rvsection=0&titles='+name+'&format=xml' | |
res = requests.get(url) | |
soup = BeautifulSoup(res.text, "xml") | |
#print soup.getText() | |
birth_re = re.search(r'(Birth date(.*?)}})', soup.revisions.getText()) | |
birth_data = birth_re.group(0).split('|') | |
print birth_data | |
print len(birth_data[2]) | |
if len(birth_data[2]) == 4: | |
return birth_data[2] | |
else: | |
return birth_data[1] | |
#dyear = wikiGet("Albert_Einstein") | |
#dyear = wikiGet("Daniel_Bleichenbacher") | |
#print dyear |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment