I have an iterator which operates on sequence of WARC documents and yields modified lists of tokens for each document:
class MyCorpus(object):
def __init__(self, warc_file_instance):
self.warc_file = warc_file_instance
def clean_text(self, html):
soup = BeautifulSoup(html) # create a new bs4 object from the html data loaded
for script in soup(["script", "style"]): # remove all javascript and stylesheet code
script.extract()
# get text
text = soup.get_text()
# break into lines and remove leading and trailing space on each
lines = (line.strip() for line in text.splitlines())
# break multi-headlines into a line each
chunks = (phrase.strip() for line in lines for phrase in line.split(" "))
# drop blank lines
text = '\n'.join(chunk for chunk in chunks if chunk)
return text
def __iter__(self):
for r in self.warc_file:
try:
w_trec_id = r['WARC-TREC-ID']
print w_trec_id
except KeyError:
pass
try:
text = self.clean_text(re.compile('Content-Length: \d+').split(r.payload)[1])
alnum_text = re.sub('[^A-Za-z0-9 ]+', ' ', text)
yield list(set(alnum_text.encode('utf-8').lower().split()))
except:
print 'An error occurred'
Now I apply apache spark paraellize to further apply desired map functions:
warc_file = warc.open('/Users/akshanshgupta/Workspace/00.warc')
documents = MyCorpus(warc_file)
x = sc.parallelize(documents, 20)
data_flat_map = x.flatMap(lambda xs: [(x, 1) for x in xs])
sorted_map = data_flat_map.sortByKey()
counts = sorted_map.reduceByKey(add)
print(counts.max(lambda x: x[1]))
I have following doubts:
- Is this the best way to achieve this or there is a simpler way?
- When I parallelise the iterator does the actual processing happen in parallel? Is is still sequential?
- What if I have multiple files? How can I scale this to a very large corpus say TB's?
