Created
November 6, 2017 04:11
-
-
Save cfilipov/f6d092046f351c9e467c8c0c6dbbc3c8 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
from bs4 import BeautifulSoup | |
import urllib2 | |
def crawl(url): | |
html = urllib2.urlopen(url).read() | |
soup = BeautifulSoup(html) | |
rows = soup.findAll("table")[3].findAll("tr") | |
for row in rows[1:]: | |
cols = row.findAll("td") | |
ahref = cols[2].findAll("a")[0] | |
ewdnum = cols[0].b.string | |
ewdnumpart = "".join([c for c in ewdnum if c.isdigit()]) | |
ewdcharpart = "".join([c for c in ewdnum if c.isalpha()]) | |
ewdpadded = ewdnumpart.zfill(4) | |
if ewdnumpart == ewdnum: | |
ewdnum = ewdpadded | |
else: | |
ewdnum = ewdpadded + ewdcharpart | |
ewdname = "EWD" + ewdnum + " " + ahref.contents[0] | |
filename = "".join([c for c in ewdname if c.isalpha() or c.isdigit() or c==' ' or c=="(" or c==")" or c=="-"]) | |
filename = filename + ".pdf" | |
pdfUrl = baseUrl + ahref["href"] | |
pdfFile = urllib2.urlopen(pdfUrl) | |
print "Saving: " + filename | |
output = open(filename, "wb") | |
output.write(pdfFile.read()) | |
output.close() | |
return | |
baseUrl = "http://www.cs.utexas.edu/~EWD/" | |
startPage = "index00xx.html" | |
html = urllib2.urlopen(baseUrl + startPage).read() | |
soup = BeautifulSoup(html) | |
links = soup.findAll("table")[1].findAll("tr")[1].findAll("p")[2].findAll(href=True) | |
for link in links: | |
crawl(baseUrl + link["href"]) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment