def parse_doc(path, icao, country, title, category):
print "Parsing AIP doc"
icao = icao.upper()
assert len(icao) == 4
url = fetchdata.getrawurl(path, country=country)
ret = dict()
ret['icao'] = icao
ret['url'] = url
ret['title'] = title
ret['name'] = icao + " - " + title
ret['category'] = category
#data,nowdate=fetchdata.getdata(path,country=country,maxcacheage=7200)
blobname = icao + "_" + category
tmppath = os.path.join(os.getenv("SWFP_DATADIR"), "aiptext", icao)
if not os.path.exists(tmppath):
os.makedirs(tmppath)
if path.lower().endswith("pdf"):
outpath_inter = os.path.join(tmppath, blobname + ".tmp.html")
def render(inputfile, outputfile):
r = "pdftohtml -c -s -i -zoom 2 -noframes -nodrm %s %s" % (
inputfile, outputfile
) #-s is not supported on older pdftohtml, and doesn't appear necessary either.
print "running", r
assert 0 == os.system(r)
fetchdata.getcreate_derived_data_raw(path,
outpath_inter,
render,
"html",
country=country)
whole = open(outpath_inter).read()
fixed = (whole.replace("<BODY bgcolor=\"#A0A0A0\"",
"<BODY bgcolor=\"#FFFFFF\"").replace(
"<TITLE>Microsoft Word - ", "<TITLE>"))
else:
assert path.endswith("html")
fixed, date = fetchdata.getdata(path, country=country)
cksum = md5.md5(fixed).hexdigest()
outpath = os.path.join(tmppath, blobname + "." + cksum + ".html")
f = open(outpath, "w")
f.write(fixed)
f.close()
#print "Wrote raw:",out,outpath
ret['checksum'] = cksum
ret['date'] = fetchdata.get_filedate(outpath)
ret['blobname'] = blobname
return ret
def getsvg(path,pagenr,usecache=True):
assert type(pagenr)==int
inputfile=fetchdata.getdatafilename(path,country="se",maxcacheage=7200)
svged=fetchdata.getcachename(path,'svg')
if os.path.exists(svged) and usecache:
cacheddate=fetchdata.get_filedate(svged)
print "Cached svg version exists, date:",svged,cacheddate
if fetchdata.is_devcomp() or datetime.now()-cacheddate<timedelta(0,86400/2):
print "Using svg cache"
try:
return open(svged).read()
except Exception,cause:
print "Couldn't read cached svg version",cause
def getsvg(path, pagenr, usecache=True):
assert type(pagenr) == int
inputfile = fetchdata.getdatafilename(path, country="se", maxcacheage=7200)
svged = fetchdata.getcachename(path, 'svg')
if os.path.exists(svged) and usecache:
cacheddate = fetchdata.get_filedate(svged)
print "Cached svg version exists, date:", svged, cacheddate
if fetchdata.is_devcomp() or datetime.now() - cacheddate < timedelta(
0, 86400 / 2):
print "Using svg cache"
try:
return open(svged).read()
except Exception, cause:
print "Couldn't read cached svg version", cause
def parse_doc(path,icao,country,title,category):
print "Parsing AIP doc"
icao=icao.upper()
assert len(icao)==4
url=fetchdata.getrawurl(path,country=country)
ret=dict()
ret['icao']=icao
ret['url']=url
ret['title']=title
ret['name']=icao+" - "+title
ret['category']=category
#data,nowdate=fetchdata.getdata(path,country=country,maxcacheage=7200)
blobname=icao+"_"+category
tmppath=os.path.join(os.getenv("SWFP_DATADIR"),"aiptext",icao)
if not os.path.exists(tmppath):
os.makedirs(tmppath)
if path.lower().endswith("pdf"):
outpath_inter=os.path.join(tmppath,blobname+".tmp.html")
def render(inputfile,outputfile):
r="pdftohtml -c -s -i -zoom 2 -noframes -nodrm %s %s"%(inputfile,outputfile) #-s is not supported on older pdftohtml, and doesn't appear necessary either.
print "running",r
assert 0==os.system(r)
fetchdata.getcreate_derived_data_raw(
path,outpath_inter,render,"html",country=country)
whole=open(outpath_inter).read()
fixed=(whole.replace("<BODY bgcolor=\"#A0A0A0\"","<BODY bgcolor=\"#FFFFFF\"")
.replace("<TITLE>Microsoft Word - ","<TITLE>"))
else:
assert path.endswith("html")
fixed,date=fetchdata.getdata(path,country=country)
cksum=md5.md5(fixed).hexdigest()
outpath=os.path.join(tmppath,blobname+"."+cksum+".html")
f=open(outpath,"w")
f.write(fixed)
f.close()
#print "Wrote raw:",out,outpath
ret['checksum']=cksum
ret['date']=fetchdata.get_filedate(outpath)
ret['blobname']=blobname
return ret
