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 re, urllib2,sys | |
| k = 0 | |
| for i in range(7,0,-1): | |
| page_url = "http://theoatmeal.com/comics_pg/page:%d"%i | |
| out = open("oatmeal\\out%d.html"%i,"w") | |
| out.write("<html><body>\n") | |
| print "getting " + page_url | |
| f = urllib2.urlopen(page_url) | |
| a = f.read() | |
| results = [] | |
| for params in re.findall("""<a href="/comics/(.*?)"><img src="(.*?)" alt="(.*?)" class="border0" /></a>""",a): | |
| title = params[2] | |
| sub_url = "http://theoatmeal.com/comics/" + params[0] | |
| print "getting " + sub_url | |
| try: | |
| sf = urllib2.urlopen(sub_url) | |
| except: | |
| print "Unexpected error:", sys.exc_info()[0] | |
| continue | |
| sa = sf.read() | |
| r1 = re.findall('"(http://s3.amazonaws.com/theoatmeal-img/comics/.*?)"',sa,re.S) | |
| result = { | |
| 'title' : title, | |
| 'sub_images' : r1 | |
| } | |
| if len(result['sub_images'])==0: | |
| print "crap" | |
| else: | |
| results += [ result ] | |
| print result | |
| results.reverse() | |
| for result in results: | |
| out.write("<hr/>\n") | |
| out.write(result['title'] + "<br/>\n") | |
| for si in result['sub_images']: | |
| print "getting " + si | |
| try: | |
| u = urllib2.urlopen(si) | |
| except: | |
| print "Unexpected error:", sys.exc_info()[0] | |
| continue | |
| fn = 'oatmeal\\%d.%s'%(k,si[-3:]) | |
| k += 1 | |
| localFile = open(fn, 'wb') | |
| localFile.write(u.read()) | |
| localFile.close() | |
| out.write("<img src=\"%s\"/> <br/>\n"%fn) | |
| out.flush() | |
| out.write("</body></html>\n"); | |
| out.close() |
