def get_all_author(self):
cur_url = "http://tuchong.com/contacts/rank/"
while True:
_logger.debug("opening initial ranking page at %s" % cur_url)
rank_page = self.br.open(cur_url, timeout=TIMEOUT).read()
soup = BeautifulSoup(rank_page)
cur_list = soup.findAll("a", {"data-site-id": True})
for author in cur_list:
self.author_to_crawl.append(author['href'])
_logger.debug('got author %s' % author['href'])
next_page_anchor = soup.findAll('a', 'next')
if (len(next_page_anchor) > 1):
_logger.fatal(
'multiple next page anchor found, url:(%s), next page number:%d'
% (cur_url, len(next_page_anchor)))
if (len(next_page_anchor) == 0):
break
cur_url = next_page_anchor[0]['href']
return self.author_to_crawl
def run(self):
while True:
self.heartbeat(pending_input=True)
self.agent.restart()
tasks = self.agent.get_all_crawler_task()
my_task = None
for task in tasks:
if task['id'] % self.shard_count == self.shard_id:
my_task = task
break
if not my_task:
_logger.debug('no task for process shard %d' % self.shard_id)
time.sleep(10)
continue
self.heartbeat(pending_input=False)
_logger.debug("Got task:%s" % (my_task))
try:
if task['ttl'] > 1:
self.process_hub(task)
elif task['ttl'] == 1:
self.process_terminal(task)
except Exception, err:
_logger.error(
'unexpected exception with url(%s):%s, %s' %
(task['anchor_url'], err, traceback.format_exc()))
finally:
def fit(self, X, y):
self.reset()
size = len(y)
for i in xrange(size):
if (i + 1) % 10000 == 0:
_logger.debug("%d processed" % (i+1))
terms = X[i]
domain = y[i]
self.training_sentence_count += 1
terms = terms.split(' ')
self.domain_count[domain] += 1
term_set = set()
for term in terms:
term = self.get_category(term)
if term in term_set:
continue
term_set.add(term)
self.terms.add(term)
self.count[term, domain] += 1
self.count[domain] += 1
self.term_count[term] += 1
self.domain_has[domain].add(term)
for domain in self.domain_has:
backoff = len(self.domain_has[domain]) * self.alpha / self.count[domain]
backoff /= len(self.term_count) - len(self.domain_has[domain])
self.domain_backoff[domain] = backoff
self.domains = self.domain_backoff.keys()
def test(model, test_file_path):
total = 0
correct = 0
decoder = NaiveDecoder(model)
outfile = open("predicted.dat", 'w')
_logger.info("Testing %s" % test_file_path)
with open(test_file_path) as test_file:
processed = 1
for line in test_file:
line = line.strip().decode('utf-8')
if not line:
continue
total += 1
sentence, tag = line.split('\t')
#sentence = extract(sentence)
result = decoder.decode(sentence)
predicted, _ = conv.argmax(result.items())
outfile.write("%s\t%s\t%s\n" % (sentence.encode('utf-8'), predicted.encode('utf-8'), tag.encode('utf-8')))
if predicted == tag:
correct += 1
if processed % 1000 == 0:
_logger.debug("%d lines processed" % processed)
processed += 1
outfile.close()
_logger.info("accuracy: %f" % (float(correct) / total))
def _sleep(self, name):
from time import sleep
if name in self._wp_config['sleep']:
_logger.debug('sleep %d seconds for %s' % (self._wp_config['sleep'][name],name))
sleep(self._wp_config['sleep'][name])
else:
_logger.debug('sleep 0.5 seconds for ' + name)
sleep(0.5)
def collect_last_term(self, X):
X_last = list()
tokens = self.last_vec.build_tokenizer()
_logger.debug("Extracting last term for each sentence")
for sent in X:
X_last.append(tokens(sent)[-1])
_logger.debug("Fitting last-term vectorizer")
return X_last
def grab_image_info_group(self, soup):
all_info = []
all_img = soup.findAll('figure', 'post-photo')
_logger.debug('%d images in group' % len(all_img))
for img in all_img:
url = img.find('a')['href']
all_info.append(self.grab_image_info(url)[0])
_logger.debug('sleeping for 5 sec')
time.sleep(5)
return all_info
def main():
_logger.info("wee indexer started")
agent = WeeSQLAgent(DB_NAME, DB_USER, DB_PASSWORD)
agent.start()
_logger.info("MySQL agent started")
indexer = Indexer(agent)
while True:
#agent.restart()
indexer.index_new_wee()
_logger.debug("Sleep for %d sec" % SLEEP_SEC)
time.sleep(SLEEP_SEC)
def bad_proxy(proxy):
proxy_log = agent.get_proxy_log(proxy)
if proxy_log == None or proxy_log['use_count'] < PROXY_TRYOUT_COUNT \
or float(proxy_log['fail_count']) / float(proxy_log['use_count']) < VALID_PROXY_FAIL_RATE:
return False
else:
_logger.debug(
"bad proxy: addr=%s, use=%d, fail=%d, fail_rate=%.2f%%" %
(proxy['addr'], proxy_log['use_count'], proxy_log['fail_count'],
float(proxy_log['fail_count']) / float(proxy_log['use_count']) *
100))
return True
def crawl_authors(self, authors, callback):
for author in authors:
cur_url = author
_logger.info("crawling author from %s" % cur_url)
try:
self.crawl_one_author(cur_url, callback)
_logger.debug('sleeping for 5 sec')
time.sleep(5)
except Exception, err:
_logger.error(
"crawl one author failed, url:(%s), error:%s, %s" %
(cur_url, err, traceback.format_exc()))
continue
def pick_proxy_for_slot(agent, slot_id, all_proxy):
proxies = [proxy for proxy in all_proxy if proxy['slot_id'] == None]
if len(proxies) == 0:
_logger.error("No free proxy for slot %d" % slot_id)
return
for proxy in proxies:
if not bad_proxy(proxy):
_logger.debug("got healthy proxy at %s" % proxy['addr'])
agent.update_proxy_slot(slot_id, proxy)
proxy['slot_id'] = slot_id
return
_logger.error("Can't find any decent proxy for slot %d" % slot_id)
def main():
_logger.info("checking dict from %s" % DICT_FILE_PATH)
agent = WeeSQLAgent(DB_NAME, DB_USER, DB_PASSWORD)
agent.start()
unindexed_terms = []
dict_file = open(DICT_FILE_PATH, 'a+')
# load all data
exists = [
term.split(' ')[1]
for term in [line for line in dict_file.read().split('\n')]
if term != ''
]
_logger.info("%d term exists in old dict" % len(exists))
terms = agent.get_all_custom_tags()
_logger.info("checking %d custom tags" % len(terms))
for term in terms:
text = term['tag']
_logger.debug('checking %s' % text)
if text.find(
' '
) == -1 and text not in exists: # ignore if text contains space
_logger.info("adding %s to dict" % text)
dict_file.write("%d %s\n" % (len(text.decode('utf-8')), text))
unindexed_terms.append(text)
dict_file.flush()
os.fsync(dict_file.fileno())
dict_file.close()
_logger.info("dict updated")
if len(unindexed_terms) > 0:
_logger.info("unindexed terms:(%s)" % ",".join(unindexed_terms))
# must import here rather than in the beginning of file
# because dict file will be read only when Indexer is imported and
# we've just updated the dict
# from indexer import Indexer
# _logger.info("need to update index for %d terms" % len(unindexed_terms))
# time.sleep(5)
# indexer = Indexer(agent)
# indexer.update_index_for_terms(unindexed_terms)
else:
_logger.info("no new tags found")
agent.stop()
def crawl_second(self, url):
self._randsleep()
_logger.debug('openning url:%s' % url)
html = self.br.open(url).read()
soup = BeautifulSoup(util.convert_to_utf8(html, "gb2312"))
for anchor in soup.findAll('a'):
try:
href = anchor['href']
# Ignore internal links
if href[:4] != "http" or href.find('hao123.com') != -1:
continue
self.output.write(' %s %s\n' % (href.encode('utf8'), anchor.text.encode('utf8')))
except Exception, err:
_logger.error('got error with anchor(%s): %s' % (str(anchor), err))
def fetch_source(self, source):
_logger.debug("pool stat: %d working %d waiting" %
(self.pool.running(), self.pool.waiting()))
_logger.info("crawling source id=%d url=%s" %
(source['id'], source['url']))
cur_time = int(time.time())
last_crawl_time = source['last_crawl_time']
if cur_time - last_crawl_time < HOUR:
_logger.info("ignore source(%s), last crawled %d minutes ago" %
(source['url'], (cur_time - last_crawl_time) / 60))
return
try:
_logger.debug("fetching feed from (%s)" % source['url'])
p = feedparser.parse(source['url'])
_logger.debug("fetched from (%s)" % source['url'])
if p.feed.has_key(
'updated_parsed') and p.feed.updated_parsed != None:
cur_feed_time = int(time.mktime(p.feed.updated_parsed))
else:
cur_feed_time = int(time.time(
)) # FeedParser doesn't understand the 'updated' field
# of this feed, neither can we. Probabaly some CJK chars.
db_feed_time = source['last_feed_time']
if db_feed_time >= cur_feed_time:
_logger.info(
"ignore source(%s), no new feed. Last feed:%s, cur feed:%s"
% (source['url'], datetime.fromtimestamp(db_feed_time),
datetime.fromtimestamp(cur_feed_time)))
self.agent.update_source_time(source)
else:
_logger.info("processing %d entries from %s" %
(len(p.entries), source['url']))
for entry in p.entries:
self.process_entry(entry, source)
self.agent.update_source_time(source, cur_feed_time)
_logger.debug(
"source(%s) updated: %s" %
(source['url'], datetime.fromtimestamp(cur_feed_time)))
_logger.info("source(id=%d) success" % source['id'])
_logger.debug("pool stat: %d working %d waiting" %
(self.pool.running(), self.pool.waiting()))
except Exception, err:
_logger.error(
"crawling faild for source id=%d, %s: %s" %
(source['id'], source['url'], traceback.format_exc()))
class FeedCrawler(object):
def __init__(self, agent, pool):
self.agent = agent
self.pool = pool
def grab_image(self, html, entry):
wee_url = entry.link.encode('utf-8')
soup = BeautifulSoup(html, fromEncoding="utf-8")
img = soup.find('img', src=True)
if img == None:
_logger.debug("%s has no image inside" % wee_url)
return
url = img['src']
_logger.debug('downloading image from %s' % url)
try:
br = pbrowser.get_browser()
image = br.download_image(url, base_url=wee_url).read()
except Exception, err:
_logger.error("downloading image failed(%s), baseurl(%s): %s" %
(url, wee_url, traceback.format_exc()))
return
try:
self.agent.add_wee_image(wee_url, image)
_logger.debug("imaged added for wee:%s" % wee_url)
except Exception, err:
_logger.error("db error, failed to add image for wee %s: %s" %
(wee_url, err))
class BrowserSinaWeibo:
def __init__(self, user=None):
self.user = user
self.selenium = selenium('localhost', 4444, 'chrome',
'http://www.baidu.com')
_logger.info('starting selenium')
self.selenium.start()
self.selenium.set_timeout(120 * 1000) # timeout 120 seconds
def _wait_load(self, minutes=1):
MIN = 60 * 1000
try:
self.selenium.wait_for_page_to_load(timeout=MIN * minutes)
except:
_logger.error(
'error waiting page to load(%d min), will continue:%s' %
(minutes, err))
def login_sina_weibo(self):
_logger.debug('logging in to t.cn')
TEN_MIN = 10 * 60 * 1000
try:
_logger.debug('try logging out, just in case')
self.selenium.click(u'link=退出')
self._wait_load()
except Exception, err:
_logger.debug('clicking loging out link failed')
# Open sina Weibo
_logger.debug('opening login page of http://t.sina.com.cn')
self.selenium.open('http://t.sina.com.cn')
self._wait_load()
self.selenium.window_maximize()
_logger.debug('filling login form')
try:
self.selenium.type('id=loginname', self.user.uname)
self.selenium.type('id=password', self.user.passwd)
self.selenium.type('id=password_text', self.user.passwd)
self.selenium.uncheck('id=remusrname')
self.selenium.click('id=login_submit_btn')
except Exception, err:
dumppath = util.dump2file_with_date(
self.selenium.get_html_source())
raise Exception(
'filling t.cn login form failed: %s, page dumped to %s' %
(err, dumppath))
def grab_image_info(self, img_url):
info = {
"title": "",
"description": "",
"binary": "",
"author": "",
"tags": "",
"ext": "",
"popularity": ""
}
_logger.debug("opening image URL: %s" % img_url)
try:
self.br.open(img_url, timeout=TIMEOUT)
except Exception, err:
_logger.error('failed to open url: %s' % img_url)
return info
def grab_image(self, html, entry):
wee_url = entry.link.encode('utf-8')
soup = BeautifulSoup(html, fromEncoding="utf-8")
img = soup.find('img', src=True)
if img == None:
_logger.debug("%s has no image inside" % wee_url)
return
url = img['src']
_logger.debug('downloading image from %s' % url)
try:
br = pbrowser.get_browser()
image = br.download_image(url, base_url=wee_url).read()
except Exception, err:
_logger.error("downloading image failed(%s), baseurl(%s): %s" %
(url, wee_url, traceback.format_exc()))
return
def spam_one_blog(self, anchor, href, target_url):
if target_url.find('/interstitial?url=') != -1:
_logger.debug('stripped %s to %s' %
(target_url, target_url[len('/interstitial?url='):]))
target_url = target_url[len('/interstitial?url='):]
error = ''
retry = 0
# Open blog post page
browser = pbrowser.get_browser()
while retry < 5:
try:
res = browser.open(target_url, timeout=10)
html = res.read()
break
except Exception, err:
error += 'open blog url failed (%d / 5):%s\n' % (retry + 1,
err)
retry += 1
def process_content(self, entry):
_logger.debug("pool stat: %d working %d waiting" %
(self.pool.running(), self.pool.waiting()))
text = ''
html = ''
if entry.has_key('summary_detail'):
content = entry.summary_detail
if content.type == u"text/plain" and text == '':
text = content.value.encode('utf-8')
elif content.type == u"text/html" and html == '':
html = content.value.encode('utf-8')
elif entry.has_key('summary'):
html = entry.summary.encode('utf-8')
if html == '' and text == '':
_logger.error("failed to get text for entry %s" %
entry.link.encode('utf-8'))
return text, html
def train(self):
self.count = defaultdict(int)
c = 0
with open(self.train_path) as infile:
for line in infile:
line = line.strip()
if not line:
continue
terms, domain = line.split('\t')
term_set = set()
for term in terms.split(' '):
term = term_category(term)
if term not in term_set:
term_set.add(term)
self.count[(term, domain)] += 1
c += 1
if c % 10000 == 0:
_logger.debug("%d records processed" % c)
def _crawl_fourth(self, url):
page = 1
while True:
_logger.debug('fourth layer page %d (%s)' % (page, url))
page += 1
self._randsleep()
html = self.br.open(url).read()
html = util.convert_to_utf8(html, 'gb2312')
soup = BeautifulSoup(html)
for td in soup.findAll('td', 'f'):
self.output.write(' %s\n' %
td.find('a').text.encode('utf-8'))
self.output.flush()
try:
url = soup.find('font',
'f9').find(text=u"下一页").parent()['href']
except:
break
def add_wee(self,
source_id,
url,
title,
text,
html,
updated_time,
author='',
tags=[]):
self.cursor.execute(
'insert into wee(source_id, url, title, text, updated_time, author, html) \
values(%s, %s, %s, %s, %s, %s, %s)',
(source_id, url, title, text, updated_time, author, html))
for tag in tags:
try:
self.cursor.execute('insert into wee_tag values(%s, %s)',
(url, tag))
except Exception, err:
_logger.debug("DB failed adding wee tag: %s" % err)
def cv(self, fold):
size = len(self.y)
kf = cross_validation.KFold(size, fold, shuffle=True)
iteration = 0
scores = list()
for train_idx, test_idx in kf:
X = [self.X[idx] for idx in train_idx]
y = [self.y[idx] for idx in train_idx]
X_test = [self.X[idx] for idx in test_idx]
y_test = [self.y[idx] for idx in test_idx]
_logger.debug("Training...")
self.fit(X, y)
_logger.debug("Testing...")
score = self.get_test_accuracy(X_test, y_test)
scores.append(score)
iteration += 1
_logger.info("CV iteration %d: CV accuracy: %f" % \
(iteration, score))
scores = np.array(scores)
return scores.mean(), scores.std()
def recursive_crawl(url, encoding, selenium, agent, domain, terminate):
if crawled_as_hub(agent, url, day_limit=3):
_logger.debug('ignore, recently(3 days) crawled as hub: %s' % (url))
return
links = pbrowser.get_all_href(url, encoding)
_logger.debug("processing %d links" % (len(links)))
count = 0
for idx, link in enumerate(links):
# ignore href to different domain; accept all href if 'domain' is empty string
if urlparse(link['href'].encode('utf-8')).netloc.find(domain) == -1:
_logger.debug('ignore (%s), different from domain (%s)' %
(link['href'].text.encode('utf-8'), domain))
continue
tweet = None
try:
#tweet = try_crawl_href(link, encoding, agent, selenium)
tweet = try_crawl_href(link['href'].encode('utf-8').lower(),
link.text.encode('utf-8').strip(), encoding,
agent, selenium)
except Exception, err:
_logger.error('crawl href failed: %s, %s' %
(err, traceback.format_exc()))
continue
if tweet != None:
count += 1
try:
agent.add_crawled_tweet(url, tweet)
_logger.info(
'new tweed added to db, %d total, (%d / %d) prcessed' %
(count, idx, len(links)))
except Exception, err:
_logger.error('failed to add crawled tweet to DB: %s' % err)
def crawl_href(anchor_url, anchor_text, encoding, selenium):
tweet = Tweet()
tweet.href = anchor_url
tweet.title = anchor_text
# get content
_logger.debug('extracting content from (%s)' % tweet.href)
content = pbrowser.extract_main_body(tweet.href, selenium, encoding)
if content == '': # we dare not to deal with article without words
return None
else:
tweet.content = content.encode('utf-8')
# get image
_logger.debug('trying to grab the main image from webpage, hint:(%s)' %
tweet.title)
image_url = ''
image = None
try:
image, image_url = pbrowser.get_main_image_with_hint(
url=tweet.href,
hint=tweet.title,
selenium=selenium,
hint_encoding=encoding)
_logger.debug('image url: %s' % image_url)
except Exception, err:
_logger.error(
'failed to grab image from %s: %s,%s' %
(tweet.href, unicode(err).encode('utf-8'), traceback.format_exc()))
def train_pair(self, p, q):
if p > q:
p, q = q, p
p_len = len(self.by_domain_data[p])
q_len = len(self.by_domain_data[q])
_logger.info("Training SVM for %s V.S. %s, %d + %d = %d recored" % \
(p, q, p_len, q_len, p_len + q_len))
X = list(self.by_domain_data[p])
X.extend(self.by_domain_data[q])
y = [p] * p_len
y.extend([q] * q_len)
pipeline = Pipeline([
("vert", TfidfVectorizer(min_df = 1, binary = False, ngram_range = (1, 1),
tokenizer = Tokenizer())),
("svm", LinearSVC(loss='l2', penalty="l1",
dual=False, tol=1e-3)),
])
if self.cv > 0:
_logger.info("Doing grid search on %d fold CV" % self.cv)
params = {
"svm__C": [1, 10, 50, 100, 500, 1000],
}
grid = GridSearchCV(pipeline, params, cv=self.cv, verbose=50)
grid.fit(X, y)
pipeline = grid.best_estimator_
_logger.info("Grid search got best score:%f" % grid.best_score_)
pipeline.accur = grid.best_score_
else:
pipeline.fit(X, y)
_logger.debug("Testing on training data")
accur = accuracy_score(y, pipeline.predict(X))
pipeline.accur = accur
_logger.info("Trainig accuracy (%s - %s): %f" % (p, q, accur))
self.svms[p,q] = pipeline
return pipeline
def process_entry(self, entry, source):
_logger.debug("pool stat: %d working %d waiting" %
(self.pool.running(), self.pool.waiting()))
url = entry.link.encode('utf-8')
if self.agent.wee_exists(url):
_logger.debug("ignore existed wee with url:%s" % url)
return
_logger.debug("processing entry from (%s)" % url)
title = entry.title.encode('utf-8')
if entry.has_key('author'):
author = entry.author.encode('utf-8')
else:
author = ''
if entry.has_key('updated_parsed') and entry.updated_parsed != None:
updated_time = int(time.mktime(entry.updated_parsed))
else:
updated_time = int(time.time(
)) # FeedParser doesn't understand the 'updated' field
# of this feed, neither can we. Probabaly some CJK chars.
text, html = self.process_content(entry)
if entry.has_key('tags'):
tags = [tag.term.encode('utf-8') for tag in entry.tags]
else:
tags = []
try:
self.agent.add_wee(source['id'], url, title, text, html,
updated_time, author, tags)
except Exception, err:
_logger.error("DB failed to add wee: %s" % traceback.format_exc())
def get_all_friend(self, callback=None):
profile_page = self.selenium.get_location()
_logger.debug('copy location url: %s' % profile_page)
_logger.debug('loading attentions page')
self.selenium.click('id=attentions')
self._wait_load()
soup = BeautifulSoup(self.selenium.get_html_source())
friends = [
self._create_user_from_attention_list(i)
for i in soup.findAll('li', 'MIB_linedot_l')
]
while True:
try:
self.selenium.click(u'下一页')
except Exception, err:
_logger.info('failed to load next page: %s' % err)
soup = BeautifulSoup(self.selenium.get_html_source())
for li in soup.findAll('li', 'MIB_linedot_l'):
friends.append(self._create_user_from_attention_list(li))
if callback != None:
callback(li)
def clean(X, y, k=10):
_logger.info("cleaning base on %d-fold cross validation" % k)
size = len(y)
kf = KFold(size, n_folds=k, shuffle=True)
fold = 1
for train_idx, test_idx in kf:
X_train, X_test = X[train_idx], X[test_idx]
y_train, y_test = y[train_idx], y[test_idx]
pipeline = Pipeline([
("vert", TfidfVectorizer(min_df = 1, binary = True, ngram_range = (1, 3),
tokenizer = Tokenizer())),
("clf", LinearSVC(loss='l1',
penalty="l2",
multi_class="ovr",
class_weight="auto")),
])
_logger.debug("Training fold %d" % fold)
pipeline.fit(X_train, y_train)
_logger.debug("Predicting for fold %d" % fold)
y_pred = pipeline.predict(X_test)
_logger.info("fold %d got accuracy: %f" % (fold, accuracy_score(y_test, y_pred)))
right_f = open("fold%d.right.dat" % fold, "w")
wrong_f = open("fold%d.wrong.dat" % fold, "w")
size = len(y_test)
for i in xrange(size):
sent, pred, gold = X_test[i].encode('utf-8'), y_pred[i].encode('utf-8'), y_test[i].encode('utf-8')
if pred != gold:
wrong_f.write("%s\t%s\t%s\n" % (pred, gold, sent))
else:
right_f.write("%s\t%s\n" % (sent, gold))
right_f.close()
wrong_f.close()
fold +=1
def login_sina_weibo(self):
_logger.debug('logging in to t.cn')
TEN_MIN = 10 * 60 * 1000
try:
_logger.debug('try logging out, just in case')
self.selenium.click(u'link=退出')
self._wait_load()
except Exception, err:
_logger.debug('clicking loging out link failed')
def crawl(self, callback=None, author_file=None):
_logger.debug("browser init finished")
self.author_to_crawl = []
if author_file == None:
authors = self.get_all_author()
# Dump authors to local file
with open("author_list", 'w') as output:
output.write("\n".join(authors))
else:
with open(author_file, 'r') as author_file_input:
authors = author_file_input.read().split()
for author in authors:
author = author.strip()
if len(author) > 0:
self.author_to_crawl.append(author)
amount = int(
math.ceil(len(self.author_to_crawl) / float(self.shard_count)))
start = self.shard_id * amount
self.author_to_crawl = self.author_to_crawl[start:start + amount]
_logger.info("crawling %d to %d" % (start, start + amount))
self.crawl_authors(self.author_to_crawl, callback)
def add_to_db(agent, info):
if info['binary'] == '':
_logger.error('info binary is empty string, ignore: %s' % info)
return
bin = info['binary']
md5 = hashlib.md5(bin).hexdigest()
if agent.pic_exists(md5):
_logger.debug("pic exists in DB, only set popularity")
agent.update_popularity(md5, info['popularity'])
return
dirpath, filepath = get_file_path_by_date(datetime.now())
if not os.path.exists(dirpath):
os.mkdir(dirpath)
filepath = filepath + "." + info['ext']
with open(filepath, "w") as output:
output.write(bin)
agent.add_pic(filepath, info['title'], info['description'], info['author'],
info['tags'], md5, info['popularity'])
def pop_tweet_stack(self, email):
if email != None:
self.cursor.execute(
'select tweet_id from tweet_stack where user_email = %s',
email)
else:
self.cursor.execute(
'select tweet_id from tweet_stack order by tweet_id desc')
if self.cursor.rowcount == 0:
_logger.debug('failed to pop tweet stack, it\'s empty, email=%s' %
email)
return None
if email == None:
all_rows = list(self.cursor.fetchall())
random.shuffle(all_rows)
else:
all_rows = self.cursor.fetchall()
for cur_row in all_rows:
tweet_id = cur_row['tweet_id']
self.cursor.execute('delete from tweet_stack where tweet_id = %s',
tweet_id)
self.conn.commit()
_logger.debug('tweet stack popped, it=%d' % tweet_id)
self.cursor.execute('select * from tweet_crawled where id = %s',
tweet_id)
if self.cursor.rowcount == 0:
_logger.debug(
'failed to find corresponding raw tweet with id = %s' %
tweet_id)
continue
raw_tweet = self.cursor.fetchone()
t = Tweet(title=raw_tweet['title'],
content=raw_tweet['content'],
href=raw_tweet['href'],
image_ext=raw_tweet['image_ext'],
image_bin=raw_tweet['image_bin'])
return t
_logger.debug('all tweet in stack tried, none ID found in DB')
return None
def crawl_one_author(self, url, callback):
page = 1
while True:
_logger.info("openning page URL: %s" % url)
self.br.open(url, timeout=TIMEOUT)
soup = BeautifulSoup(self.br.response().read())
url = self.br.geturl()
img_div = soup.findAll('div', 'images')
imgs = list(
itertools.chain(
*[div.findAll('a', target='_blank') for div in img_div]))
imgs.extend(soup.findAll('a', {'data-location': 'content'}))
_logger.debug("%d images on this page" % len(imgs))
for a in imgs:
img_url = a['href']
if img_url in self.crawl_history:
_logger.debug('ignoring crawled URL: %s' % img_url)
continue
info = None
try:
all_info = self.grab_image_info(img_url)
self.logfile.write(img_url + '\n')
self.logfile.flush()
_logger.debug('image processed %s' % img_url)
except Exception, err:
_logger.error(
'processing one image url failed, url:%s, %s' %
(img_url, err))
else:
for info in all_info:
try:
if callback != None:
callback(info=info)
except Exception, err:
_logger.error(
'callback failed, image url: %s, %s, %s' %
(img_url, err, traceback.format_exc()))
_logger.debug('sleeping for 5 sec')
time.sleep(5)
def transform(self, X, y = None):
#return self.count_vec.transform(X)
_logger.debug("Doing tfidf transform")
Xc = self.count_vec.transform(X)
X_last = self.collect_last_term(X)
_logger.debug("Doing last term transform")
Xl = self.last_vec.transform(X_last)
_logger.debug("stacking features")
ret = sparse.hstack([Xc, Xl])
tokens = self.count_vec.build_tokenizer()
l = list()
for sent in X:
terms = tokens(sent)
l.append(1 if ("__LOCATION__" in terms and "__ORGNIZATION__" in terms) else 0)
l = np.array(l)
l.shape = len(l), 1
ret = sparse.hstack([ret, l])
_logger.debug("vectorization transform done")
return ret
def add_wee_source(self, url, pr=0, tags=[]):
source_id = self.get_source_id(url)
if source_id == -1:
_logger.debug("source(%s) doesn't exist, will insert" % url)
self.cursor.execute(
"insert into wee_source(url, pr) values(%s, %s)", (url, pr))
self.conn.commit()
source_id = self.get_source_id(url)
_logger.debug("source(%s) id fetched: %d" % (url, source_id))
for tag in tags:
tag = tag.encode('utf-8')
self.cursor.execute("insert ignore into source_tag values(%s, %s)",
(source_id, tag))
self.conn.commit()
_logger.debug('tag %s added to source %d' % (tag, source_id))
def try_crawl_href(anchor_url, anchor_text, encoding, agent, selenium):
_logger.debug('crawling anchor (%s), URL: %s' % (anchor_text, anchor_url))
# filters
# ignore bad-looking anchors
if util.chinese_charactor_count(anchor_text.decode('utf-8')) < 10:
_logger.debug('too few chinese chars in anchor text, ignoring')
return None
# ignore same href crawled recently
if crawled_as_terminal(agent, anchor_url, anchor_text, 30):
_logger.debug('ignore %s, same href was crawled %d days ago' %
(anchor_url, (now - last_crawled_at).days))
return None
tweet = crawl_href(anchor_url, anchor_text, encoding, selenium)
_logger.info('crawl_href finished, anchor-text:(%s)' % anchor_text)
return tweet
def fit(self, X, y = None):
_logger.debug("Fitting count vectorizer")
self.count_vec.fit(X)
X_last = self.collect_last_term(X)
self.last_vec.fit(X_last)
return self
