def scrape_links(self,pos):
doc_object=MongoDB.get(URLQueue,'document',number=pos)
while doc_object is not None:
self.scrape_link_and_child(doc_object['url'])
pos=MongoDB.increment_url_counter()
doc_object=MongoDB.get(URLQueue,'document',number=pos)
def save_top_urls_to_mongo(cls):
with open(settings.OUTPUT_FILE,encoding='ISO-8859-1') as input:
for webpage in input:
#dictionary of webpage properties
webpage_dict=cls.__get_url_properties_and_sanitize(webpage)
MongoDB.save_modify_url(**webpage_dict)
return cls
def scrape_urls(cls):
position=MongoDB.get(MetaData,'position',type='queue')
WebScraper().scrape_links(position)
return cls
def scrape(self):
home=self.http.get(dmoz_home)
home_page_links=self._scrapeHomeAndGetLinks(home.data)
#visit each link in homepage and dig down
#for url in home_page_links:
i=0
while i<settings.NUM_RANDOM_WEBPAGE:
result=self._scrapPage(home_page_links[random.randint(0,len(home_page_links)-1)])
if result is not None and MongoDB.get_url_object(result['url']) is None:
i+=1
try:
page=utf_8_safe_decode(self.http.get(result['url']).data)
MongoDB.save_modify_url(page=page,**result)
Logger.info("Completed: "+result['url'])
except Exception as ex:
Logger.error(ex)
def scrape_link_and_child(self,parent_url):
parent_url=base_util.replace_dot_url(parent_url)
webpage_body,parent_url=self.scrape(base_util.unreplace_dot_url(parent_url),None)
#exit if failed to scrap website
if webpage_body is None:
return
MongoDB.save_page(url=parent_url,page=webpage_body)
Logger.info('Completed page: '+parent_url)
#Now, we grab the childs of this webpage
all_ahref=[base_util.combine_parent_rel_link(parent_url,a.attrs['href']) for a in BeautifulSoup(webpage_body,'html.parser', from_encoding="utf-8").find_all('a') if 'href' in a.attrs]
child_urls=random.sample(all_ahref,settings.GET_X_CHILD) if len(all_ahref)>=settings.GET_X_CHILD else all_ahref
#get rid of bad normalization
if not re.match('^www[.].*$',parent_url):
Logger.info('Updating bad url for {}'.format(parent_url))
MongoDB.update_url(base_util.normalize_url(parent_url),parent_url)
if len(child_urls) > 0:
parent_genres=MongoDB.get_genre(parent_url)
#get the childs
for child_url in child_urls:
child_page=self.scrape(child_url,parent_url)
if child_page is None:
exploredset=set()
tries=0
for url in set(all_ahref)^(exploredset):
if tries==settings.MAX_RETRIES:
Logger.info('Max retrie number exceeded')
break
Logger.info("trying new url: "+url)
child_page=self.scrape(url,parent_url)
if child_page is not None:
break
exploredset.add(url)
tries+=1
if child_page is not None:
MongoDB.save_modify_url(url=base_util.replace_dot_url(child_url),parent=[MongoDB.get_url_object(parent_url)],genre=parent_genres,page=child_page)
Logger.info('Completed page: '+child_url)
edit_distance = sys.maxsize
alexa_genre_length += len(alexa_genre_name)
for dmoz_genre_name, dmoz_genre_info in dmoz_dict.items():
if edit_distance is 0:
break
if alexa_genre_name == dmoz_genre_name:
exact_match += 1
edit_distance = 0
else:
edit_distance = min(edit_distance, levenshtein(dmoz_genre_name, alexa_genre_name))
if edit_distance is not sys.maxsize:
total_edit_distance += edit_distance
edit_distance_count += 1
return {
"alexa_total": len(alexa_dict),
"edit_distance_count": edit_distance_count,
"total_edit_distance": total_edit_distance,
"alexa_match": exact_match,
"alexa_genre_length": alexa_genre_length,
}
# accumulate stats and update the collection
MongoDB.connect(settings.HOST_NAME, settings.PORT)
def start(cls):
MongoDB.connect(settings.HOST_NAME,settings.PORT)
return cls
def create_url_queue(cls):
for num,URL_document in enumerate(URLToGenre.objects):
MongoDB.push_to_queue(num,URL_document)
return cls
