def parse_feed(self, entry):
'Extract list of articles from the feed.'
articles = []
(url, publisher, publisher_location) = entry
try:
c = urlopen(url)
except URLError:
print 'Failed to fetch ' + url
feed = feedparser.parse(c)
# for e in feed.entries[:1]: # read just the first entry while debugging
for e in feed.entries:
image_link = None
image_type = None
for link in e.links:
if link['rel'] == 'enclosure':
image_link = link['href']
image_type = link['type']
article = Article(
publisher=publisher,
publisher_location=publisher_location,
published_date=e.updated_parsed,
title=e.title,
link=e.link,
image_link=image_link,
image_type=image_type)
content = self.htmlparser.parse(e.link)
m = re.search(r'-\s*([a-zA-Z]+(,?\s+[a-zA-Z]+){0,6})$', content)
if m:
article.source = m.group(1)
article.content = re.sub(r'(\\n)?\s*-\s*([a-zA-Z]+(,?\s+[a-zA-Z]+){0,6})$', '', content)
article.store(self.db) # put article and word frequencies into couchdb
articles.append(article)
return articles
def parse_feed(self, feed):
'Extract list of articles from the feed.'
articles = []
htmlparser = HtmlParser()
for e in feed.entries[:1]: # read just the first entry while debugging
article = Article(source=e.author, title=e.title, link=e.link)
content = htmlparser.parse(e.link)
article.content = re.sub(r' -.*$', '', content)
article.save() # and associated word frequencies
articles.append(article)
return articles
def process_item(self, item, spider):
article = Article()
article.title = item["title"]
article.create_date = item["create_date"]
article.content = remove_tags(item["content"]).strip().replace("\r\n","").replace("\t","")
article.front_image_url = item["front_image_url"]
# article.front_image_path = item["front_image_path"]
article.praise_nums = item["praise_nums"]
article.comment_nums = item["comment_nums"]
article.fav_nums = item["fav_nums"]
article.url = item["url"]
article.tags = item["tags"]
article.id = item["url_object_id"]
title_suggest = self.gen_suggests(article.title, article.tags)
article.title_suggest = title_suggest
article.save()
return item
def save_to_es(self):
article = Article()
article.title = self['title']
article.create_date = self["create_date"]
article.content = remove_tags(self["content"])
article.front_image_url = self["front_image_url"]
if "front_image_path" in self:
article.front_image_path = self["front_image_path"]
article.praise_nums = self["praise_nums"]
article.fav_nums = self["fav_nums"]
article.comment_nums = self["comment_nums"]
article.url = self["url"]
article.tags = self["tags"]
article.meta.id = self["url_object_id"]
article.title_suggest = gen_suggests(Article._doc_type.index, ((article.title, 7), (article.tags, 8)))
article.save()
redis_cli.incr("jobbole_count")
return
