Created
June 6, 2017 14:14
-
-
Save chapter09/4c25e2efbb856b804e1c5fdf95616181 to your computer and use it in GitHub Desktop.
Parsing tpc address & affiliation
This file contains hidden or 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
#!/usr/local/bin/python3 | |
import codecs | |
import re | |
name_addr = {} | |
with codecs.open('./tpc', encoding='utf-8') as infd: | |
for line in infd.readlines(): | |
if "(" not in line: | |
continue | |
name = line.split("(")[0][1:].strip() | |
addr = line.split(",")[1].strip() | |
name_addr[name] = addr | |
new_fd = open('./tpc_new.html', 'w', encoding='utf-8') | |
with codecs.open('./tpc.html', encoding='utf-8') as old_fd: | |
for line in old_fd.readlines(): | |
if re.search(r'.*\(.*\)$', line): | |
if ',' not in line: | |
name = line.split("(")[0][1:].strip() | |
addr = name_addr[name] | |
line = line[:-2]+", "+addr | |
new_fd.write(line) | |
else: | |
new_fd.write(line) | |
else: | |
new_fd.write(line) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment