def process(fullpath, config, rcontext, columns=None):
parser = tika.AutoDetectParser()
input = tika.FileInputStream(tika.File(fullpath))
content = tika.BodyContentHandler()
metadata = tika.Metadata()
context = tika.ParseContext()
parser.parse(input, content, metadata, context)
content = content.toString()
processed = [
metadata.get("Creation-Date"),
metadata.get("Last-Modified"),
metadata.get("Last-Save-Date"),
metadata.get("Revision-Number"),
metadata.get("Author"),
metadata.get("Last-Author"),
metadata.get("Template"),
metadata.get("Word-Count"),
metadata.get("title"),
metadata.get("subject"),
metadata.get("Company"),
metadata.get("Keywords"),
metadata.get("Page-Count"),
metadata.get("Character Count"), content
]
extract.tika_extract(fullpath, context, metadata, config, rcontext)
return processed
def process(fullpath, config, rcontext, columns=None):
parser = tika.AutoDetectParser()
input = tika.FileInputStream(tika.File(fullpath))
content = tika.BodyContentHandler()
metadata = tika.Metadata()
context = tika.ParseContext()
parser.parse(input,content,metadata,context)
content = content.toString()
processed = [
metadata.get("Creation-Date"),
metadata.get("Last-Modified"),
metadata.get("Last-Save-Date"),
metadata.get("Author"),
metadata.get("producer"),
metadata.get("xmpTPg:NPages"),
content
]
extract.xpdf_extract(fullpath, config, rcontext)
return processed
def process(fullpath, config, rcontext, columns=None):
results = []
meta = []
parser = tika.AutoDetectParser()
input = tika.FileInputStream(tika.File(fullpath))
content = tika.BodyContentHandler()
metadata = tika.Metadata()
context = tika.ParseContext()
parser.parse(input, content, metadata, context)
content = content.toString()
for n in metadata.names():
meta.append(metadata.get(n))
val = 0
parse = [0, 3, 4, 7, 9]
for x in meta:
if val in parse:
results.append(x)
val += 1
results.append(content)
extract.tika_extract(fullpath, context, metadata, config, rcontext)
return results
def __handler(stream):
handler = tika.ToHTMLContentHandler()
met = tika.Metadata()
pc = tika.ParseContext()
parser = tika.AutoDetectParser()
parser.parse(stream, handler, met, pc)
return handler.toString()
def __parse(stream):
parsed = {}
parser = tika.AutoDetectParser()
content = tika.BodyContentHandler(-1)
metadata = tika.Metadata()
context = tika.ParseContext()
parser.parse(stream, content, metadata, context)
parsed["content"] = content.toString()
parsed["metadata"] = {}
for n in metadata.names():
parsed["metadata"][n] = metadata.get(n)
return parsed
def __parse(stream):
if not tika.getVMEnv():
raise RuntimeError("tika.initVM() not called")
parsed = {}
parser = tika.AutoDetectParser()
content = tika.BodyContentHandler()
metadata = tika.Metadata()
context = tika.ParseContext()
parser.parse(stream, content, metadata, context)
parsed["content"] = content.toString()
parsed["metadata"] = {}
for n in metadata.names():
parsed["metadata"][n] = metadata.get(n)
return parsed