def from_html(html, url=None, download_date=None):
"""
Extracts relevant information from an HTML page given as a string. This function does not invoke scrapy but only
uses the article extractor. If you have the original URL make sure to provide it as this helps NewsPlease
to extract the publishing date and title.
:param html:
:param url:
:return:
"""
extractor = article_extractor.Extractor(
['newspaper_extractor', 'readability_extractor', 'lang_detect_extractor'])
title_encoded = ''.encode()
if not url:
url = ''
# if an url was given, we can use that as the filename
filename = urllib.parse.quote_plus(url) + '.json'
item = NewscrawlerItem()
item['spider_response'] = DotMap()
item['spider_response'].body = html
item['url'] = url
item['source_domain'] = urllib.parse.urlparse(url).hostname.encode() if url != '' else ''.encode()
item['html_title'] = title_encoded
item['rss_title'] = title_encoded
item['local_path'] = None
item['filename'] = filename
item['download_date'] = download_date
item['modified_date'] = None
item = extractor.extract(item)
tmp_article = ExtractedInformationStorage.extract_relevant_info(item)
final_article = ExtractedInformationStorage.convert_to_class(tmp_article)
return final_article
def from_html(html, url=None):
"""
Extracts relevant information from an HTML page given as a string. This function does not invoke scrapy but only
uses the article extractor.
:param html:
:param url:
:return:
"""
extractor = article_extractor.Extractor(
['newspaper_extractor', 'readability_extractor', 'date_extractor', 'lang_detect_extractor'])
title_encoded = ''.encode()
if not url:
url = ''
# if an url was given, we can use that as the filename
filename = urllib.parse.quote_plus(url) + '.json'
item = NewscrawlerItem()
item['spider_response'] = DotMap()
item['spider_response'].body = html
item['url'] = url
item['source_domain'] = urlparse(url).hostname.encode() if url != '' else ''.encode()
item['html_title'] = title_encoded
item['rss_title'] = title_encoded
item['local_path'] = None
item['filename'] = filename
item['download_date'] = None
item['modified_date'] = None
item = extractor.extract(item)
article = ExtractedInformationStorage.extract_relevant_info(item)
return DotMap(article)
