本文整理汇总了Python中readability.readability.Document.summary方法的典型用法代码示例。如果您正苦于以下问题：Python Document.summary方法的具体用法？Python Document.summary怎么用？Python Document.summary使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类readability.readability.Document的用法示例。
在下文中一共展示了Document.summary方法的15个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: markdownify
# 需要导入模块: from readability.readability import Document [as 别名]
# 或者: from readability.readability.Document import summary [as 别名]
def markdownify(url_list, **options):
articles = []
images = []
paragraph_links = options['paragraph_links']
wrap_text = options['wrap_text']
preamble = options['preamble']
for url in url_list:
req = urllib2.Request(url,None,{'Referer': url_list[0]})
html = urllib2.urlopen(req).read()
document = Document(html, url=url)
readable_title = document.short_title()
summary = document.summary()
summary_doc = build_doc(summary)
images.extend([a.get('src') for a in summary_doc.findall('.//img')])
articles.append(document.summary())
markdown_articles = []
for (article, url) in zip(articles, url_list):
h = html2text.HTML2Text(baseurl=url)
h.inline_links = False
h.links_each_paragraph = (paragraph_links and 1) or 0
h.body_width = (wrap_text and 78) or 0
markdown_articles.append(h.handle(article))
combined_article = u"\n\n----\n\n".join(markdown_articles)
if preamble:
combined_article = (u"Title: %s \nOriginal URL: %s\n\n" % (readable_title, url_list[0])) + combined_article
return combined_article.encode("utf-8")示例2: strip_chapter
# 需要导入模块: from readability.readability import Document [as 别名]
# 或者: from readability.readability.Document import summary [as 别名]
def strip_chapter(self, html):
"""
Strips chapter and gets relevant HTML using Readability
:param html: str
:return:
"""
doc = Document(html)
if len(doc.summary()) <= 20:
content = str(BeautifulSoup(html, 'html.parser').find_all('div', class_=self.main_content_div)[0])
content = '<html><head><meta charset="utf-8"></head>' + content + '</html>'
return doc.short_title(), content
return (doc.short_title(),
str(doc.summary()).replace('<html>', '<html><head><meta charset="utf-8"></head>'))示例3: extract_article
# 需要导入模块: from readability.readability import Document [as 别名]
# 或者: from readability.readability.Document import summary [as 别名]
def extract_article(url):
r = requests.get(url)
# the the url exists, continue
if r.status_code == 200:
# extract and parse response url
url = parse_url(r.url)
# extract html
html = r.content.decode('utf-8', errors='ignore')
# run boilerpipe
BP = Extractor(html=html)
# run readability
Rdb = Document(html)
html = Rdb.summary()
# return article data
return {
'extracted_title': Rdb.short_title().strip(),
'extracted_content': strip_tags(BP.getText()),
}
# otherwise return an empty dict
else:
return {}示例4: extract_article
# 需要导入模块: from readability.readability import Document [as 别名]
# 或者: from readability.readability.Document import summary [as 别名]
def extract_article(url):
r = requests.get(url)
# the the url exists, continue
if r.status_code == 200:
# extract and parse response url
url = parse_url(r.url)
# extract html
html = r.content.decode('utf-8', errors='ignore')
# run boilerpipe
# boilerpipe_extractor = Extractor(html=html)
# run readability
readability_extractor = Document(html)
html = readability_extractor.summary()
# return article data
return {
'title': readability_extractor.short_title(),
'html': html,
'content': strip_tags(html).encode('utf-8', errors='ignore'),
'url': url
}
# otherwise return an empty dict
else:
return {}示例5: enrich
# 需要导入模块: from readability.readability import Document [as 别名]
# 或者: from readability.readability.Document import summary [as 别名]
async def enrich(self, result):
if not self.soup:
return result
result.set('title', self.soup.title.string, 0, 'textlength')
if result.has('content'):
return result
parts = []
for txt in self.soup.find_all("noscript"):
if txt.string is not None:
parts.append(txt.string)
html = " ".join(parts).strip()
if not html:
html = self.soup.all_text()
try:
doc = Document(html, url=self.url)
content = doc.summary(html_partial=True)
result.set('content', sanitize_html(content))
# pylint: disable=bare-except
except:
pass
return result示例6: find_full_text
# 需要导入模块: from readability.readability import Document [as 别名]
# 或者: from readability.readability.Document import summary [as 别名]
def find_full_text(html_source):
doc = Doc(html_source)
content = doc.summary()
stripped = strip_tags(content)
stripped = to_plain_text(stripped)
return stripped示例7: __init__
# 需要导入模块: from readability.readability import Document [as 别名]
# 或者: from readability.readability.Document import summary [as 别名]
class Article:
def __init__(self, url):
print('Saving page: {}'.format(url))
res = requests.get(url)
self.url = url
self.article = Document(res.content)
self._add_title()
self._save_images()
def _add_title(self):
self.root = etree.fromstring(self.article.summary())
body = self.root.find('body')
title = self.article.title()
ascii_title = unidecode(title) if type(title) == unicode else title
title_header = etree.HTML('<h2>{}</h2>'.format(ascii_title))
body.insert(0, title_header)
def _save_images(self):
tmppath = tempfile.mkdtemp()
images = self.root.xpath('//img')
for img in images:
imgsrc = img.get('src')
# handle scheme-agnostic URLs
if 'http' not in imgsrc and '//' in imgsrc:
imgsrc = 'http:{}'.format(imgsrc)
# handle relative file paths
elif 'http' not in imgsrc:
parsed = urlparse(self.url)
imgsrc = '{}://{}{}'.format(parsed.scheme, parsed.netloc, imgsrc)
filename = os.path.basename(imgsrc)
dest = os.path.join(tmppath, filename)
try:
res = requests.get(imgsrc)
except Exception as e:
print('Could not fetch image ({}) from "{}"'.format(str(e), imgsrc))
return
if res.status_code == 404:
print('Could not fetch image (HTTP 404), attempted fetch: "{}", source URL: {}'.format(imgsrc, img.get('src')))
continue
with open(dest, 'wb') as f:
f.write(res.content)
img.set('src', dest)
@property
def title(self):
return self.article.title()
@property
def html(self):
return etree.tostring(self.root)示例8: set
# 需要导入模块: from readability.readability import Document [as 别名]
# 或者: from readability.readability.Document import summary [as 别名]
class Gist:
keyword_pattern = re.compile(r'^[^\d]+$')
stop_words = set(get_stop_words('en'))
def __init__(self, html):
self.html = html
self.document = Document(html)
@property
def title(self):
return self.document.short_title()
@cached_property
def text(self):
text = self.document.summary()
text = re.sub('<br[^>]+>', '\n', text)
text = re.sub('</?p[^>]+>', '\n\n', text)
text = re.sub('<[^>]+>', '', text)
text = re.sub('^[ \t]+$', '', text)
text = re.sub('\n{3,}', '\n\n', text, flags=re.MULTILINE)
return text
@staticmethod
def _common_prefix(one, two):
parallelity = [x == y for x, y in zip(one, two)] + [False]
return parallelity.index(False)
@classmethod
def _find_representative(cls, stem, text):
tokens = text.split()
prefixes = {token: cls._common_prefix(token, stem) for token in tokens}
best = lambda token: (-token[1], len(token[0]))
return sorted(prefixes.items(), key=best)[0][0]
@classmethod
def _is_good_keyword(cls, word):
return (word not in cls.stop_words) and \
cls.keyword_pattern.match(word)
@classmethod
def find_keywords(cls, text):
whoosh_backend = SearchForm().searchqueryset.query.backend
if not whoosh_backend.setup_complete:
whoosh_backend.setup()
with whoosh_backend.index.searcher() as searcher:
keywords = searcher.key_terms_from_text(
'text', text, numterms=10, normalize=False)
keywords = list(zip(*keywords))[0] if keywords else []
keywords = [cls._find_representative(keyword, text) for keyword in keywords]
keywords = [keyword for keyword in keywords if cls._is_good_keyword(keyword)]
#no double keywords in list
keywords = list(set(keywords))
#no punctuation in suggested keywords
keywords = [''.join(c for c in s if c not in string.punctuation) for s in keywords]
return keywords
@property
def keywords(self):
return self.find_keywords(self.text)示例9: run
# 需要导入模块: from readability.readability import Document [as 别名]
# 或者: from readability.readability.Document import summary [as 别名]
def run(index):
print "Index %d" % index
dirname = "data/%04d" % index
# url of english article
url = open(dirname + "/url_en.txt").read()
# download html
html = urllib.urlopen(url).read().decode('latin-1')
# apply readability
document = Document(html)
article = document.summary()
article = nltk.clean_html(article)
# replace latin characters
article = re.sub(u' ', u'\n', article)
article = re.sub(u'\x92', u'`', article)
article = re.sub(u'\x96', u'-', article)
# article_en.txt
output = codecs.open(dirname + "/article_en.txt", 'w', encoding='ascii', errors='ignore')
output.write(article)
output.close()
# title.txt
output = codecs.open(dirname + "/title.txt", 'w', encoding='ascii', errors='ignore')
output.write(document.title())
output.close()示例10: main
# 需要导入模块: from readability.readability import Document [as 别名]
# 或者: from readability.readability.Document import summary [as 别名]
def main():
html = urllib.urlopen("http://habrahabr.ru/post/150756/").read()
doc = Document(html)
short_title = doc.short_title()
readable_article = doc.summary()
f = open("C:\\users\\mykola\\documents\\%s.html" % short_title, "wb")
f.write(readable_article.encode("utf-8"))
f.close()示例11: _getResponseText
# 需要导入模块: from readability.readability import Document [as 别名]
# 或者: from readability.readability.Document import summary [as 别名]
def _getResponseText(self, response):
'''
(reponse) -> Text
Returns text within the body of an HttpResponse object.
'''
readability = Document(response.body)
content = readability.title() + readability.summary()
return content示例12: crawl_url
# 需要导入模块: from readability.readability import Document [as 别名]
# 或者: from readability.readability.Document import summary [as 别名]
def crawl_url(url):
html = requests.get(url)
doc = Document(html.content)
content = doc.summary().encode('utf-8')
title = doc.title().encode('utf-8')
return {
'content': content,
'title': title
}示例13: get_article_from_item
# 需要导入模块: from readability.readability import Document [as 别名]
# 或者: from readability.readability.Document import summary [as 别名]
def get_article_from_item(self, item):
url = item['link']
logging.debug(url)
author = 'n/a'
if item.has_key('author'):
author = item.author
html = urllib.urlopen(url).read()
doc = Document(html)
return Article(doc.title(), doc.short_title(), author, doc.summary())示例14: extract_data
# 需要导入模块: from readability.readability import Document [as 别名]
# 或者: from readability.readability.Document import summary [as 别名]
def extract_data(self, patchurl):
try:
f = requests.get(patchurl)
html = f.content
doc = Document(html)
title = doc.short_title()
summary = doc.summary()
return smart_str(title), smart_str(summary)
except:
return None, None示例15: body_via_readability
# 需要导入模块: from readability.readability import Document [as 别名]
# 或者: from readability.readability.Document import summary [as 别名]
def body_via_readability(page_html, source_url):
"""
Readbility is good at article + title.
"""
obj = Document(page_html)
body = obj.summary()
if not body:
return None
return html.prepare(body, source_url)