def gather_links_save_page(page_url):
html_string = ''
try:
response = urlopen(page_url, timeout=10)
if 'text/html' in response.getheader('Content-Type'):
html_bytes = response.read()
html_string = html_bytes.decode("utf-8")
if Crawler.save_html_pages:
# By running concurrent threads this creates multiple equal codes
code = Crawler.count_code
Crawler.count_code += 1
write_file(Crawler.pages_folder + str(code), html_string)
Crawler.code_from_url[page_url] = code
Crawler.url_from_code[code] = page_url
if code % 100 == 0:
print(
'storing with pickle: code_from_url and url_from_code'
)
with open('code_from_url_dict.pickle', 'wb') as handle:
pickle.dump(Crawler.code_from_url,
handle,
protocol=pickle.HIGHEST_PROTOCOL)
with open('url_from_code_dict.pickle', 'wb') as handle:
pickle.dump(Crawler.url_from_code,
handle,
protocol=pickle.HIGHEST_PROTOCOL)
# with open('filename.pickle', 'rb') as handle:
# b = pickle.load(handle)
link_extractor = LinkExtractor(Crawler.base_url, page_url, True,
Crawler.domain_name)
link_extractor.feed(html_string)
except Exception as e:
print(str(e))
return set()
return link_extractor.page_links()
def preprocess_documents(self):
global link_extractor
web_graph = graph.OptimizedDirectedGraph()
with open('code_from_url_dict.pickle', 'rb') as handle:
code_from_url = pickle.load(handle)
# for filename in os.listdir(self.FOLDER + '/pages/'):
for filename in range(self.n_pages):
with open(self.FOLDER + '/pages/' + str(filename)) as f:
doc_text = f.read()
if doc_text is None:
print('empty doc')
print(filename)
continue
self.process_page(int(filename), doc_text)
link_extractor = LinkExtractor(self.FOLDER, self.HOMEPAGE,
self.DOMAIN_NAME)
link_extractor.feed(doc_text)
links = link_extractor.page_links()
# print('document number '+filename)
# print('total links: '+str(len(links)))
count = 0
web_graph.add_node(int(filename))
for url in links:
if url in code_from_url:
# if code_from_url[url] == 6:
# print(url)
# exit()
count += 1
web_graph.add_edge(int(filename), code_from_url[url])
# print('node '+filename+str(web_graph.get_pointing_to(int(filename))))
return web_graph
