Python Article.title方法代码示例

# 需要导入模块: from article import Article [as 别名]
# 或者: from article.Article import title [as 别名]
    def add_feed(self, feed):
        """
        add_feed takes the URL or file path of a Feedzilla feed, cleans it up,
        and adds the articles this Feed object's list.
        """

        log.info("Retrieving feed.")

        f = feedparser.parse(feed)
        for item in f['entries']:
            a = Article()

            # Set ID as integer, without feedzilla at beginning
            a.id = item['id']
            a.id = re.sub(r'.*feedzilla\.com:(.*)', r'\1', a.id)
            a.id = int(a.id)

            if a.id not in self.articles.keys():
                # Set source, author and title
                a.author = item['author']
                a.title = item['title']
                a.source=item['source']['links'][0]['href']
                a.trueSource="http://news.feedzilla.com/en_us/stories/world-news/"+str(a.id)

                # Set summary, get rid of all the junk at the end
                summary = item['summary']
                summary = summary[:summary.find("\n\n")]
                summary = summary[:summary.find("<")]
                a.summary = summary

                # Add the article if it doesn't already exist
                self.articles[a.id] = a

# 需要导入模块: from article import Article [as 别名]
# 或者: from article.Article import title [as 别名]
    def add_feed(self, feed):
        print "Adding feed =>",
        
        f = feedparser.parse(feed)
        for item in f['entries']:
            a = Article()
            
            # Set ID as integer, without feedzilla at beginning
            a.id = item['id']
            a.id = re.sub(r'.*feedzilla\.com:(.*)', r'\1', a.id)
            a.id = int(a.id)
            
            if a.id not in self.articles.keys():
                # Set source, author and title
                a.author = item['author']
                a.title = item['title']
                a.source=item['source']['links'][0]['href']
                a.trueSource="http://news.feedzilla.com/en_us/stories/world-news/"+str(a.id)

                # Set summary, get rid of all the junk at the end
                summary = item['summary']
                summary = summary[:summary.find("\n\n")]
                summary = summary[:summary.find("<")]
                a.summary = summary
            
                # Add the article if it doesn't already exist
                self.articles[a.id] = a

        print "Done"

# 需要导入模块: from article import Article [as 别名]
# 或者: from article.Article import title [as 别名]
def step1_extract_raw_files():
    file = open('cranfield_collection.txt', 'r')
    line_index = 1

    # jump to first title
    file.readline()
    next_line = file.readline()

    # extract data
    while next_line != "":
        article = Article()
        # index
        article.index = line_index
        line_index += 1

        article.title = Utils.get_next_content(file, ".A")
        article.author = Utils.get_next_content(file, ".B")
        article.bubble = Utils.get_next_content(file, ".W")
        article.content = Utils.get_next_content(file, ".I")

        Utils.step1_write(article)

        next_line = file.readline()

    print("completed!")

# 需要导入模块: from article import Article [as 别名]
# 或者: from article.Article import title [as 别名]
 def single_parsed_directory(parsed_articles_file):
     articles = []
     print("Parsing " + parsed_articles_file)
     feed_file = open(parsed_articles_file, "r")
     lines = feed_file.readlines()
     for line in lines[1:]:
         parts = line.split('\t')
         article = Article()
         article.id = parts[0]
         article.feed = parts[1]
         article.time = parts[2]
         article.title = parts[3]
         article.text = parts[4]
         article.add_tag(parts[5].replace("\"", ""))
         articles.append(article)
     feed_file.close()
     return articles

# 需要导入模块: from article import Article [as 别名]
# 或者: from article.Article import title [as 别名]
    def __init__(self, line):
        self.info = defaultdict(str)
        self.line = line

        self.in_the_news = False
        self.duplicate = False

        if re.search('^https?://', line):
            obj = Article(line)
        else:
            obj = Radio(line)

        config = Config()
        obj.config_values = config[line]

        # we format here instead of in Article/Radio in case
        # we ever want/need to change the format
        if obj.date():
            self.info["date"] = obj.date().strftime("%m/%d/%Y")
            self.info["datetime_date"] = obj.date()
        else:
            self.info["date"] = ""

        self.info["medium"]    = obj.medium()
        self.info["format"]    = obj.format()
        self.info["media"]     = obj.media()
        self.info["title"]     = obj.title()
        self.info["author"]    = obj.author()
        self.info["mentioned"] = obj.mentioned()
        self.info["topic"]     = ""
        self.info["positive"]  = obj.positive()
        self.info["franklin"]  = obj.franklin()
        self.info["duration"]  = obj.duration()

        if isinstance(obj, Article):
            self.info["url"] = obj.url
            self.in_the_news = 'in the news' in line.lower()
            self.in_print = 'in print' in line.lower()
            self.duplicate = 'and online' in line.lower() #should this be for both Radio and Article?
        else:
            self.info["url"] = ""

        self.info["orig"] = line

# 需要导入模块: from article import Article [as 别名]
# 或者: from article.Article import title [as 别名]
    def parseArticle(self, baseUrl, link):
        data = self.readUrl(link)

        searchItems = re.findall(
            r'<article class="news-article">.*?<div class="article-info">.*?<div class="col-sm-3 col-xs-6">.*?<strong>EMITIRANO</strong>:<br>(.+?)</div>.*?</div>.*?<div id="jplayer_container" class="audio-player  played repeat-on">.*?<div class="track-info">.*?<p class="track-title">(.+?)</p>.*?<div class="download-section">.*?<h4>Preuzmite datoteku</h4>.*?<a href="(.+?)" class="attachment-file">.*?<span class="file-size pull-right">(.+?)</span>.*?</a>.*?</div>.*?<blockquote>.*?<h3>.*?</h3>.*?<p>(.+?)</p>.*?</blockquote>.*?</article>',
            data,
            re.DOTALL,
        )

        if not searchItems:
            return None

        article = Article()
        article.pubDate = searchItems[0][0].strip()
        article.title = searchItems[0][1].strip()
        article.link = baseUrl + searchItems[0][2].strip()
        # article.size = searchItems[0][3].strip()
        article.description = searchItems[0][4].strip()

        return article

# 需要导入模块: from article import Article [as 别名]
# 或者: from article.Article import title [as 别名]
    def createArticle(self, baseUrl, articleData):
        data = self.readUrl(baseUrl + articleData[0])

        chennelDatas = re.findall(
            r'<div class="main-content">.*?<article class="article-content">.*?<div class="user-content">.*?<h1>(.*?)</h1>.*?</article>.*?<script type="text/javascript">.*?mp3: "(.+?)".*?</script>.*?</div>',
            data, re.DOTALL)

        article = Article()
        article.title = chennelDatas[0][0]
        article.link = chennelDatas[0][1]
        article.pubDate = articleData[2]
        article.description = ''

        descriptionDatas = re.findall(r'<p class="description">(.+?)</p>', data, re.DOTALL)
        if len(descriptionDatas) > 0:
            article.description = descriptionDatas[0]
        else:
            descriptionDatas = re.findall(r'<div class="content">.*?<p>(.+?)</p>.*?</div>', data, re.DOTALL)
            if len(descriptionDatas) > 0:
                article.description = descriptionDatas[0]

        return article