本文整理汇总了Python中article.Article.parse方法的典型用法代码示例。如果您正苦于以下问题：Python Article.parse方法的具体用法？Python Article.parse怎么用？Python Article.parse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article.Article的用法示例。
在下文中一共展示了Article.parse方法的3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: _parse
# 需要导入模块: from article import Article [as 别名]
# 或者: from article.Article import parse [as 别名]
def _parse(self):
article = Article(self.data["url"])
# Fake article.download()
article.download_date = datetime.utcnow()
article.source_domain = urlparse(article.url).netloc
article.html = self.data["html"]
article.parse()
self.article = article示例2: menuable_articles
# 需要导入模块: from article import Article [as 别名]
# 或者: from article.Article import parse [as 别名]
def menuable_articles (self) :
lines = self.__load_content_lines ()
menu = self.__load_book_menu (lines)
articles = self.__parse_articles (lines, menu)
for art in articles :
start_line = art['start_line']
end_line = art['end_line']
author = art['author']
title = art['title']
print "%06d, %06d, %s, %s" % (start_line, end_line, author, title)
contents = lines[start_line : end_line]
contents.insert(0, title.encode('utf8'))
contents.insert(1, author.encode('utf8'))
article = Article()
article.parse(contents, self.outer)示例3: multiple_articles
# 需要导入模块: from article import Article [as 别名]
# 或者: from article.Article import parse [as 别名]
def multiple_articles (self) :
lines = self.__load_content_lines ()
page_number = re.compile(u'\u00b7\d+\u00b7');
#pattern = re.compile('[\ufb00-\ufffd]\d+[\ufb00-\ufffd]');
texts = []
for line_orig in lines :
line = line_orig.decode('utf8')
line = line.strip(u'\u3000 \t\r\n')
if not line :
continue
if re.search (page_number, line) :
line = line.encode('utf8')
if len(texts) > 0 :
article = Article()
article.parse(texts, self.outer)
texts = []
else :
line = line.encode('utf8')
texts.append(line)