def get_next_level_page(self, soup):
page_links = []
for link in soup.find_all('a'):
if not link.get('href'):
continue
newlink = urljoin(self.page.url, link.get('href'))
retlink = vc.various_check(newlink)
if retlink:
page_links.append(retlink)
page_links = list(set(page_links))
for link in page_links:
if not self.check_duplication(link):
page = Page(link, self.page.depth + 1, self.page.score, ref=self.page.url)
self.queue.en_queue(page)
def query(self):
''' send google search query and get the top 10 result as a list of URLs '''
if self.fake:
return ['http://engineering.nyu.edu', 'http://www.nyu.edu']
my_referer = 'https://www.bing.com/'
headers = {
'User-Agent':
'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.157 Safari/537.36',
'referer': my_referer
}
''' send query and return list of URLs '''
query_string = self.make_query_string()
params = {'q': query_string}
# make google HTTP request
bing_url = "http://www.bing.com/search?"
try:
response = requests.get(bing_url,
params=params,
headers=headers,
timeout=0.5)
except Exception as e:
return
# parse page contents
data = response.text
soup = BeautifulSoup(data, 'html.parser')
ret = []
for link in soup.find_all('h2'):
for linka in link.find_all('a'):
if linka.get('href'):
newlink = urljoin(response.url, linka.get('href'))
if newlink.startswith('http'):
retlink = vc.various_check(newlink)
if retlink:
ret.append(retlink)
# return array of URls in an array
return list(set(ret))[:10]
def query(self):
''' send google search query and get the top 10 result as a list of URLs '''
if self.fake:
return ['http://engineering.nyu.edu', 'http://www.nyu.edu']
my_referer='http://www.google.com'
headers = {
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_9_5) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/44.0.2403.157 Safari/537.36',
'referer': 'http://www.google.com'
}
''' send query and return list of URLs '''
query_string = self.make_query_string()
params = {'q':query_string}
# make google HTTP request
google_url = "http://www.google.com/search?"
try:
response = requests.get(google_url, params=params, headers=headers, timeout=0.5)
except Exception as e:
self.error = 1
return
# parse page contents
data = response.text
soup = BeautifulSoup(data, 'html.parser')
ret = []
for link in soup.find_all('h3'):
for linka in link.find_all('a'):
if not linka.get('style'):
if linka.get('href'):
newlink = urljoin(response.url, linka.get('href'))
retlink = vc.various_check(newlink)
if retlink:
ret.append(retlink)
# return array of URls in an array
return list(set(ret))[:10]
def get_next_level_page(self, soup):
page_links = []
for link in soup.find_all('a'):
if not link.get('href'):
continue
newlink = urljoin(self.page.url, link.get('href'))
retlink = vc.various_check(newlink)
if retlink:
page_links.append(retlink)
page_links = list(set(page_links))
for link in page_links:
if not self.check_duplication(link):
page = Page(link,
self.page.depth + 1,
self.page.score,
ref=self.page.url)
self.queue.en_queue(page)
