def fetch_pages_helper(self, urls, start, step, cache, results):
"""
Helper function for parallel fetching
"""
max_size = 5000000
pages = []
for i in range(start, len(urls), step):
url = urls[i]
if (i + 1) % 500 == 0:
print "Fetched ", i, " urls"
page = Page(url)
try:
text = ''
size = 0
res = requests.get(url,
headers=self.header,
verify=False,
timeout=5,
stream=True)
#t = time.time()
for chunk in res.iter_content(10000):
#if (time.time() - t) > 5:
# break
# raise ValueError('timeout reached')
text += chunk
size += len(chunk)
if size > max_size:
print "Size exceeds ", size
raise ValueError('response too large')
if res.status_code == 200:
#page = Page(url)
if len(text) < self.max_html_size:
page.add_html(text)
else:
print "Failed to fetch ", url, res.status_code, start
except:
print "Failed to fetch ", url
continue
# Save to cache. Note that always save the fetched pages even if the requests were failed
# since we want to avoid re-fetch these pages in the future
if self.caching:
cache.add(url, page.get_json_obj())
else:
page.get_json_obj() # hack
if page.body and (len(page.get_text('body')) > 100):
#if not page.is_empty():
pages.append(page)
results.put(pages)
def fetch(self, urls, out_file, extraction=True):
"""
Parameters:
-----------
urls: list of url. Each url represents a website
Returns:
--------
list<website>: list of fetched websites
"""
if os.path.exists(out_file):
fetched_urls = []
with open(out_file) as lines:
for line in lines:
try:
jsobj = json.loads(line)
fetched_urls.append(jsobj['url'])
except:
traceback.print_exc()
urls = [url for url in urls if url not in fetched_urls]
print "Number of urls to fetch: ", len(urls)
out = open(out_file, 'a+')
for i, url in enumerate(urls):
if (i + 1) % 20 == 0:
print "Fetched ", i, " urls"
try:
res = requests.get(url,
headers=self.header,
verify=False,
timeout=10)
if res.status_code == 200:
page = Page(url)
if len(res.text) < self.max_html_size:
page.add_html(res.text)
if extraction:
jspage = page.get_json_obj()
else:
jspage = {'url': url, 'html': res.text}
out.write(json.dumps(jspage) + '\n')
else:
print res.status_code, url
except:
print "Failed to fetch ", url
traceback.print_exc()
out.close()
