sam/AutomatedFanfic
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Code cleanup, now uses temporary directories for safety

Browse Source
This commit is contained in:
MrTyton 2016-09-07 06:08:36 -04:00
parent e83d954a6c
commit d4c0779dec
1 changed files with 54 additions and 54 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

108
fanficdownload-cleaned.py
View File

@ -1,5 +1,4 @@
from fanficfare import geturls from fanficfare import geturls
import os
from os import listdir, remove, rename, utime from os import listdir, remove, rename, utime
from os.path import isfile, join from os.path import isfile, join
from subprocess import check_output, STDOUT from subprocess import check_output, STDOUT
@ -7,6 +6,8 @@ import logging
from optparse import OptionParser from optparse import OptionParser
import re import re
from ConfigParser import ConfigParser from ConfigParser import ConfigParser
from tempfile import mkdtemp
from shutil import rmtree
logging.getLogger("fanficfare").setLevel(logging.ERROR) logging.getLogger("fanficfare").setLevel(logging.ERROR)
@ -25,6 +26,17 @@ def parse_url(url):
url = neutral.search(url).group(1) url = neutral.search(url).group(1)
return url return url
def get_files(mypath, filetype=None, fullpath=False):
ans = []
if filetype:
ans = [f for f in listdir(mypath) if isfile(join(mypath, f)) and f.endswith(filetype)]
else:
ans = [f for f in listdir(mypath) if isfile(join(mypath, f))]
if fullpath:
return [join(mypath, f) for f in ans]
else:
return ans
def main(user, password, server, label, inout_file, path="", ): def main(user, password, server, label, inout_file, path="", ):
if path != "": if path != "":
@ -43,68 +55,56 @@ def main(user, password, server, label, inout_file, path="", ):
if len(urls) != 0: print "URLs to parse: {}".format(", ".join(urls)) if len(urls) != 0: print "URLs to parse: {}".format(", ".join(urls))
files = lambda x: [f for f in listdir(x) if isfile(join(x, f))] loc = mkdtemp()
for url in urls: for url in urls:
print "Working with url {}".format(url) print "Working with url {}".format(url)
storyId = None
try: try:
res = check_output('calibredb search "Identifiers:{}" {}'.format(url, path), shell=True,stderr=STDOUT) res = check_output('calibredb search "Identifiers:{}" {}'.format(url, path), shell=True,stderr=STDOUT)
storyId = res storyId = res
print "\tStory is in calibre with id {}".format(storyId) print "\tStory is in calibre with id {}".format(storyId)
try: print "\tExporting file"
print "\tExporting file" res = check_output('calibredb export {} --dont-save-cover --dont-write-opf --single-dir --to-dir "{}" {}'.format(storyId, loc, path), shell=True)
res = check_output('calibredb export {} --dont-save-cover --dont-write-opf --single-dir {}'.format(storyId, path), shell=True) cur = get_files(loc, ".epub", True)[0]
onlyfiles = files(".") print '\tDownloading with fanficfare, updating file "{}"'.format(cur)
for cur in onlyfiles: moving=""
if not cur.endswith(".epub"): continue
print '\tDownloading with fanficfare, updating file "{}"'.format(cur)
res = check_output('fanficfare -u "{}" --update-cover'.format(cur), shell=True,stderr=STDOUT)
#print res
if "already contains" in res:
print "\tIssue with story, FF.net site is broken."
fp.write("{}\n".format(url))
remove(cur)
continue
elif "Story does not exist" in res:
print "\tInvalid URL"
continue
elif "more recently than Story" in res:
print "\tForcing download update\n"
res = check_output('fanficfare -u "{}" --force --update-cover'.format(cur), shell=True,stderr=STDOUT)
print "\tRemoving {} from library".format(storyId)
res = check_output('calibredb remove {} {}'.format(storyId, path), shell=True,stderr=STDOUT)
#print res
print "\tAdding {} to library".format(cur)
res = check_output('calibredb add "{}" {}'.format(cur, path), shell=True,stderr=STDOUT)
res = check_output('calibredb search "Identifiers:{}" {}'.format(url, path), shell=True, stderr=STDOUT)
print "\tAdded {} to library with id {}".format(cur, res)
#print res
remove(cur)
except Exception as e:
print "\tSomething fucked up: {}".format(e)
remove(cur)
fp.write("{}\n".format(url))
except: except:
print "\tStory is not in calibre" #story is not in calibre
try: cur = url
res = check_output('fanficfare -u "{}" --update-cover'.format(url), shell=True) moving = 'cd "{}" && '.format(loc)
#print res try:
onlyfiles = files(".") res = check_output('{}fanficfare -u "{}" --update-cover'.format(moving, cur), shell=True,stderr=STDOUT)
for cur in onlyfiles:
if not cur.endswith(".epub"): continue if "already contains" in res:
try: raise ValueError("Issue with story, site is broken. Story likely hasn't updated on site yet.")
print "\tAdding {} to library".format(cur) elif "Story does not exist" in res:
res = check_output('calibredb add "{}" {}'.format(cur, path), shell=True, stderr=STDOUT) raise ValueError("Invalid URL")
#print res elif "more recently than Story" in res:
remove(cur) print "\tForcing download update\n"
except Exception: res = check_output('{}fanficfare -u "{}" --force --update-cover'.format(moving, cur), shell=True,stderr=STDOUT)
remove(cur) cur = get_files(loc, '.epub', True)[0]
raise except Exception as e:
except Exception as e: print "Exception: {}".format(e)
print "\tSomething fucked up: {}".format(e) rmtree(loc)
fp.write("{}\n".format(url)) loc = mkdtemp()
fp.write("{}\n".format(url))
continue
if storyId:
print "\tRemoving {} from library".format(storyId)
res = check_output('calibredb remove {} {}'.format(storyId, path), shell=True,stderr=STDOUT)
print "\tAdding {} to library".format(cur)
res = check_output('calibredb add "{}" {}'.format(cur, path), shell=True,stderr=STDOUT)
res = check_output('calibredb search "Identifiers:{}" {}'.format(url, path), shell=True, stderr=STDOUT)
print "\tAdded {} to library with id {}".format(cur, res)
remove(cur)
rmtree(loc)
if __name__ == "__main__": if __name__ == "__main__":