def parse_forum(self, response):
hxs = HtmlXPathSelector(response)
text = hxs.select('//div[@class="forumPostText"]').extract()
time = hxs.select('//div[@class="forumPostTitle"]/div[@class="floatRight"]/text()').extract()
author = hxs.select('//div[@class="forumUsername"]/a/text()').extract()
items = []
for i in range(0,len(text)):
texts =''.join(BeautifulSoup(text[i]).findAll(text=True))
if time[i]:
thetime = time[i].strip()
thetime = datetime.strptime(thetime, '%d.%m.%Y %H:%M:%S').strftime('%Y-%m-%d %H:%M:%S')
else:
thetime= '2012-10-14 20:24:02'
if getIdentifier(texts,thetime) in self.stored:
raise DropItem("Duplicate item found")
else:
item = CrawlerItem()
item['url'] = response.url
item['texts'] =texts
item['time'] = thetime
item['author'] = author[i]
item['source'] = 'forum'
item['site'] = 'Holiday Check'
item['location'] = 'Schweiz'
item['crawltime'] = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
item['identifer'] = getIdentifier(texts, thetime)
self.stored.append(getIdentifier(texts,thetime))
items.append(item)
return items
def parse(self, response):
hxs = HtmlXPathSelector(response)
hasdiscus = hxs.select('//div[@class="noTalkback"]')
if not hasdiscus:
items = []
text = hxs.select('//div[@class="komment"]/p/span').extract()
user = hxs.select('//div[@class="kommentLeft"]/h4/text()').extract()
time =hxs.select('//div[@class="kommentTime"]/text()').extract()
if text:
for i in range(0,len(text)):
dates = datetime.strptime(time[i][:-12], '%d.%m.%Y').strftime('%Y-%m-%d')
texts =''.join(BeautifulSoup(text[i]).findAll(text=True))
texts = texts.strip()
indeti = getIdentifier(texts,dates)
item = CrawlerItem()
item['url'] = response.url
item['texts'] = text[i]
item['time'] = dates
item['author'] = user[i]
item['source'] = 'Comments'
item['site'] = 'Tagesanzeiger'
item['location'] = 'Schweiz'
item['identifer'] = indeti
item['crawltime'] = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
if (indeti not in self.stored):
self.stored.append(indeti)
items.append(item)
return items
def parse_advisor(self, response):
hxs = HtmlXPathSelector(response)
text = hxs.select('//div[@id="singleLeft"]/p').extract()
date = hxs.select('//span[@class="publishedDate"]/text()').extract()
dates = date[0].replace('(Erstellt: ','')
dates = datetime.strptime(dates[:-12], '%d.%m.%Y').strftime('%Y-%m-%d')
s = ""
items = []
for i in range(0,len(text)):
texts = ''.join( BeautifulSoup( text [i]).findAll( text = True ))
texts =texts.replace('var badword = 0;', '')
texts =texts.replace('var badwordserch = 1;', '')
texts =texts.replace(date[0], '')
texts = texts.strip()
s +=texts
if s:
indeti = getIdentifier(s,dates)
if (indeti in self.stored):
raise DropItem("Duplicate item found")
else:
item = CrawlerItem()
item['url'] = response.url
item['texts'] = s
item['time'] = dates
item['author'] = 'Tagi'
item['source'] = 'Zeitung'
item['site'] = 'Tagesanzeiger'
item['location'] = 'Schweiz'
item['identifer'] = indeti
item['crawltime'] = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
self.stored.append(indeti)
return item