"""
import sys
import httplib
import re
import fetcher
#url -- proceeding page url
url = "http://dblp.uni-trier.de/db/conf/acl/acl2011.html"
if (len(sys.argv) > 1):
url = sys.argv[1]
index = 0
contents = fetcher.fetch_webpage(url)
paper_links = re.findall('<br><a href="(.*?)"><img alt="Electronic Edition"', contents)
paper_names = re.findall('<b>(.*?)[\.|\?]', contents)
if len(paper_names) != len(paper_links):
print "fetch paper names & links error!"
else:
for paper_link in paper_links :
if paper_link.endswith(".pdf") :
d_link = paper_link
else :
real_path = re.findall('<a href="(.*?)"', fetcher.fetch_webpage(paper_link))
if len(real_path) == 0 :
index = index + 1
continue
d_link = real_path[0]
if (len(sys.argv) > 1):
pNo = sys.argv[1]
if (len(sys.argv) > 2):
size = int(sys.argv[2])
detail_list_url = "http://acm.lib.tsinghua.edu.cn/acm/Detail-List.nsp?&view=ACM&cid_PCODE=&cid_DOCTYPE=&cid_HASABSTRACT=&cid_HASFULLTEXT=&lastquery=(pNo):PROC_ID&sortfield=SECTION_SEQ_NO,SEQ_NO,PUBDATE&sortorder=ASCENDING,ASCENDING,ASCENDING&var_AUTHCODE=&var_PUBCODE=&var_BROWSECODE=&var_SOURCECODE=&recid=&reccode=&mailto=&docindex=iNo&var_SECTION=&numresults=25&fromrecord=&usertag="
content_url = "http://166.111.120.94/acm/ContentLoader.nsp?view=path"
file_url = "http://166.111.120.94/acm/path"
detail_list_url = detail_list_url.replace("pNo", pNo, 1)
for i in range(0, size) :
contents = fetcher.fetch_webpage(detail_list_url.replace("iNo", str(i), 1))
paper_name = re.findall('<b><img src="img/spacer.gif"><br>(.*?)</b>', contents);
#print paper_name
paper_path = re.findall('fl = "(.*?)"', contents)
p_len = len(paper_path)
index = 0
while index < p_len:
if not paper_path[index].endswith(".pdf") :
del paper_path[index]
p_len = p_len - 1
else :
index = index + 1
if len(paper_path) == 0 :
continue
real_path = re.findall('top.location.replace\("(.*?)"', fetcher.fetch_webpage(content_url.replace("path", paper_path[0], 1)))
