def extract_content(page_id, ext_id, htmlReturn=False): # htmlReturn=False: by default returns text content
if (page_id is None or "") or (ext_id is None or ""): return badrequest()
page = Page.get_page(page_id)
if page is None: return documentnotfound()
extraction = Extraction.get_extraction(ext_id)
if extraction is None: return documentnotfound()
original_content = page.content
if original_content is None or original_content is "": return nocontent()
if not jpype.isThreadAttachedToJVM():
jpype.attachThreadToJVM()
extractor = Extractor(extractor='DefaultExtractor', html=original_content)
if not htmlReturn:
bp_content = extractor.getText()
else:
bp_content = extractor.getHTML()
if bp_content is None: nocontent()
extraction.update(bp_content=bp_content)
return success()
def __init__(self, url):
if not jpype.isThreadAttachedToJVM():
jpype.attachThreadToJVM()
BoilerpipeWrapperWrapper.iUrl = url