def parse_mini_card(self, response):
if response.status == 404:
yield response.meta['uItem']
yield response.meta['item']
pItem = response.meta['item']
user = response.xpath('//a[@target="_blank"]/@href').extract()[0]
uid = user.split('/')[-1]
pItem['uid'] = uid
if uid in self.users:
yield pItem
return
self.users.add(uid)
item = userItem()
item['disPage'] = pItem['disPage']
item['uid'] = uid
name = response.xpath(
'//h5[@class="userInfo__content-name"]/text()').extract()[0]
item['firstName'], item['lastName'] = self.getName(name)
item['source'] = response.urljoin(user)
request = scrapy.Request(item['source'],
callback=self.parse_profile,
dont_filter=True)
request.meta['item'] = item
request.meta['pItem'] = pItem
yield request
def parse_author(self, response, disPage):
item = userItem()
item['disPage'] = disPage
user = response.xpath(
'//div[@class="author-details"]//a/@href').extract()[0]
item['uid'] = user.split('/')[-1]
item['source'] = response.urljoin(user)
firstName = response.xpath(
'//span[@class="given-name"]/text()').extract()
lastName = response.xpath(
'//span[@class="family-name"]/text()').extract()
if firstName:
item['firstName'] = firstName[0]
if lastName:
item['lastName'] = lastName[0]
occupation = response.xpath(
'//div[@class="agent-details-col"]/div/text()').extract()
if occupation:
item['occupation'] = occupation[0].strip()
rainmaker = response.xpath('//div[@class="agent-mast-img"]/div')
if rainmaker:
item['account'], item['points'] = self.getRainmaker(rainmaker)
location = response.xpath(
'//div[@id="find_agents"]/p/a/@href').extract()
if location:
item['state'], item['city'] = [i.split('/')[-1] for i in location]
return item
def parse_user(self, c, disPage):
item = userItem()
item['disPage'] = disPage
user = c.xpath('div[@class="comment-left-section"]/a/@href').extract()
if not user:
user = c.xpath('.//div[@class="comment-author"]/text()').extract()
item['uid'] = user[0].split('/')[-1]
item['source'] = 'http://activerain.com' + user[0]
name = c.xpath('.//div[@class="comment-author"]/text()').extract()[0]
item['firstName'], item['lastName'] = self.getName(name)
occupation = c.xpath('.//div[@class="tagline"]/text()').extract()
if occupation:
item['occupation'] = occupation[0].strip()
rainmaker = c.xpath('.//div[@class="comment-header"]/div')
if rainmaker:
item['account'], item['points'] = self.getRainmaker(rainmaker)
location = c.xpath('.//div[@class="company"]/text()').extract()
if location:
l = location[0].split('-')[-1].strip()
if ',' in l:
item['city'], item['state'] = l.split(',') if l else (None,
None)
return item
def parse_comments(self, response):
blog = response.meta['blog']
count = blog['count']
d = json.loads(response.text)
for id in d:
for i in d[id]:
count += 1
c = Selector(text=i)
item = postItem()
uItem = userItem()
item['URL'] = blog['URL']
item['title'] = blog['title']
item['disPage'] = blog['blogPage']
item['pid'] = int(
c.xpath('//div[@class="blog-comment-comment "]/@data-id').
extract()[0])
item['replyid'] = count
t = c.xpath(
'.//meta[@itemprop="datePublished"]/@content').extract()[0]
item['postTime'] = datetime.strptime(t, '%Y-%m-%dT%H:%M:%S')
item['replyTo'] = blog['replyid'].get(id)
# Ignore deleted post
if not item['replyTo']:
continue
body = c.xpath(
'.//div[@class="blog-comment-comment-body"]//text()'
).extract()
item['body'] = ''.join(body).strip()
uid = c.xpath(
'//div[@class="blog-comment-comment-details"]/div/@data-id'
).extract()[0]
item['uid'] = uid
uItem['uid'] = uid
name = c.xpath(
'//div[contains(@class, "agent-tag")]/text()').extract()[0]
uItem['firstName'], uItem['lastName'] = self.getName(name)
url = 'http://activerain.com/profile/{0}/mini_vcard'.format(
uid)
request = scrapy.Request(url,
callback=self.parse_mini_card,
dont_filter=True)
request.meta['item'] = item
request.meta['uItem'] = uItem
request.meta['handle_httpstatus_list'] = [404]
yield request
