Created
April 17, 2015 14:24
-
-
Save krishnakummar/4c074b36ce83f74d586e to your computer and use it in GitHub Desktop.
Fetching medicine names from medindia
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
import requests | |
import BeautifulSoup | |
import string | |
session = requests.session() | |
alphas = list(string.ascii_uppercase) | |
for i in alphas: | |
url_parse = "http://www.medindia.net/drugs/manufacturers.asp?alpha=" + i | |
req = session.get(url_parse) | |
doc = BeautifulSoup.BeautifulSoup(req.content) | |
manufacturers_div = doc.find("div", attrs={"class": "headlines clear-fix"}) | |
for manu in manufacturers_div: | |
tag = manu.next | |
links = tag.parent | |
pnames = links.findAll("a") | |
for name in pnames: | |
try: | |
phar_link = name["href"] | |
pro_req = session.get(phar_link) | |
pro_doc = BeautifulSoup.BeautifulSoup(pro_req.content) | |
manu_products = pro_doc.find("div", attrs={"class": "top-gray col-list clear-fix "}) | |
product_names = manu_products.findAll("h3") | |
trade_names = manu_products.findAll("div", attrs={"class": "links"}) | |
for i in xrange(0,len(product_names)): | |
tnames = trade_names[i].contents | |
list2 = [a for a in tnames if a != '\n'] | |
list3 = [b for b in list2 if b is not None and b != '|'] | |
for item in list3: | |
if item.string.strip() != "|": | |
try:print name.string.strip() + "," + product_names[i].string.strip() + ","+item.string.strip()+","+phar_link.strip() | |
except:pass | |
except:pass | |
break |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment