def crawl_url():
global errors_encountered
print "\n* NEW CRAWLING SESSION FOR CONFIG URL: %s *\n" % seed_url
while len(urls_to_visit) > 0:
current_url = urls_to_visit.pop(0)
try:
time.sleep(request_delay)
page_source = None
met_mimetype_criteria = False
met_file_extension_criteria = False
write_file = False
# Write url to file if file name provided
if url_file:
with open(url_file, "a") as fw:
fw.write(current_url + os.linesep)
print "\nProcessing URL: %s\n" % current_url
# Look for a valid head response from the URL
print "HEAD Request of URL: ", current_url
head_response = requests.head(current_url, allow_redirects=True, headers=REQUEST_HEADERS, timeout=60)
if not head_response.status_code == requests.codes.ok:
print "Received an invalid HEAD response for URL: ", current_url
else:
content_type = head_response.headers.get('content-type')
encoding = head_response.encoding
final_url = head_response.url
# If we found an HTML file, grab all the links
if 'text/html' in content_type:
print "Requesting URL with Python Requests: ", current_url
get_response = requests.get(current_url, headers=REQUEST_HEADERS, timeout=60)
content_type = get_response.headers.get('content-type')
encoding = get_response.encoding
page_source = get_response.text
final_url = get_response.url
if 'text/html' in content_type and not "<body" in page_source:
print "No <body> tag found in page source. Requesting URL with Selenium: ", final_url
try:
browser.get(final_url)
page_source = browser.page_source
except:
print "First Selenium request failed. Trying one last time."
browser.get(final_url)
page_source = browser.page_source
else:
if 'text/html' in content_type and not "<body" in page_source:
print "No <body> tag found in page source. Requesting URL with Selenium one last time."
browser.get(final_url)
page_source = browser.page_source
final_url = browser.current_url
add_new_urls(final_url, page_source)
# Check if we should write files with this mimetype or extension
for mimetype in mimetypes_list:
if mimetype in content_type:
met_mimetype_criteria = True
if not met_mimetype_criteria:
url_parsed = urlparse.urlsplit(final_url)
url_path = url_parsed.path.strip()
for file_extension in file_extensions_list:
if url_path.endswith(file_extension):
met_file_extension_criteria = True
# Check if we should write this file based on potential regex restrictions, only if it passes the mimetype or extension tests
if met_mimetype_criteria or met_file_extension_criteria:
if not using_regex_filters:
write_file = True
else:
for regex_filter in regex_filters:
if regex_filter.search(final_url):
write_file = True
break
# Write a file if we need to
if write_file:
print "Need to write file"
if not page_source:
print "Requesting URL with Python Requests: ", final_url
get_response = requests.get(final_url, headers=REQUEST_HEADERS, timeout=60)
encoding = get_response.encoding
page_source = get_response.text
final_url = get_response.url
encoded_data, encoding_used = get_encoded_data(page_source, encoding)
filepath = get_filepath(final_url, encoding_used, output_dir)
with open(filepath, 'w') as f:
f.write(encoded_data)
print "Wrote file: %s with encoding: %s" % (filepath, encoding_used)
global files_written
files_written += 1
global files_processed
files_processed += 1
print "Files Found: %d Processed: %d Remaining: %d Written: %d Operational Errors: %d" % ( len(all_urls), files_processed, len(urls_to_visit), files_written, errors_encountered )
except:
errors_encountered += 1
try:
traceback_info = '\n'.join(traceback.format_exception(*(sys.exc_info())))
except:
traceback_info = ''
print "*** ERROR PROCESSING: %s ***\nTraceback: %s\n" % ( current_url, traceback_info )
def main(argv):
input_file = None
output_dir = None
failed_urls = []
errors_encountered = 0
try:
opts, args = getopt.getopt(argv, "i:o:")
except getopt.GetoptError:
print USAGE_MESSAGE
sys.exit(2)
for opt, arg in opts:
if opt == "-i":
input_file = arg
if opt == "-o":
output_dir = arg
if not input_file or not output_dir:
print USAGE_MESSAGE
sys.exit(2)
if os.path.isdir(output_dir):
print "Found directory: %s" % output_dir
else:
mkdir_p(output_dir)
print "Created directory: %s" % output_dir
with open(input_file) as f:
urls = f.readlines()
print "Found %d URLs" % len(urls)
browser = get_selenium_browser()
for url in urls:
url = url.strip()
if not url:
continue
try:
print "\nProcessing URL: %s" % url
print "Requesting URL with Python Requests: ", url
get_response = requests.get(url,
headers=REQUEST_HEADERS,
timeout=60)
content_type = get_response.headers.get('content-type')
encoding = get_response.encoding
page_source = get_response.text
final_url = get_response.url
if 'text/html' in content_type and not "<body" in page_source:
print "No <body> tag found in page source. Requesting URL with Selenium: ", final_url
try:
browser.get(final_url)
page_source = browser.page_source
except:
print "First Selenium request failed. Trying one last time."
browser.get(final_url)
page_source = browser.page_source
else:
if 'text/html' in content_type and not "<body" in page_source:
print "No <body> tag found in page source. Requesting URL with Selenium one last time."
browser.get(final_url)
page_source = browser.page_source
final_url = browser.current_url
print "Found final URL: %s" % final_url
encoded_data, encoding_used = get_encoded_data(
page_source, encoding)
filepath = get_filepath(final_url, encoding_used, output_dir)
with open(filepath, 'w') as f:
f.write(encoded_data)
print "Wrote file: %s with encoding: %s" % (filepath,
encoding_used)
except:
errors_encountered += 1
failed_urls.append(url)
try:
traceback_info = '\n'.join(
traceback.format_exception(*(sys.exc_info())))
except:
traceback_info = ''
print "*** ERROR PROCESSING: %s ***\nTraceback: %s\n" % (
url, traceback_info)
print "\nOperational Errors: %d\n" % errors_encountered
if failed_urls:
print "The following %d URLs failed:" % len(failed_urls)
for url in failed_urls:
print url
from functions import access_folder, get_filepath, read_folder, get_date_str
import os
data = get_date_str()
filepath = get_filepath()
files = read_folder(filepath)
def put_files_sftp(conn):
if conn.pwd == "/":
print(conn.listdir())
if "folder" in conn.listdir():
access_folder(conn, "folder", conn.listdir())
else:
folder = input()
access_folder(conn, folder, conn.listdir())
print(conn.listdir())
arq = conn.listdir()
arq.remove(arq[1])
if arq[0]:
access_folder(conn, arq[0], arq)
if conn.listdir():
print("There are files of last week in the folder. Them weren't processed yet. Contact the developer.")
else:
for file in files:
localpath = filepath + "uploads/"
try:
conn.put(localpath, '', callback=None, confirm=True)
print("Transfering...{}".format(file))
os.rename(filepath + file, localpath + data + "/" + file)
def main(argv):
input_file = None
output_dir = None
failed_urls = []
errors_encountered = 0
try:
opts, args = getopt.getopt(argv, "i:o:")
except getopt.GetoptError:
print USAGE_MESSAGE
sys.exit(2)
for opt, arg in opts:
if opt == "-i":
input_file = arg
if opt == "-o":
output_dir = arg
if not input_file or not output_dir:
print USAGE_MESSAGE
sys.exit(2)
if os.path.isdir(output_dir):
print "Found directory: %s" % output_dir
else:
mkdir_p(output_dir)
print "Created directory: %s" % output_dir
with open(input_file) as f:
urls = f.readlines()
print "Found %d URLs" % len(urls)
browser = get_selenium_browser()
for url in urls:
url = url.strip()
if not url:
continue
try:
print "\nProcessing URL: %s" % url
print "Requesting URL with Python Requests: ", url
get_response = requests.get(url, headers=REQUEST_HEADERS, timeout=60)
content_type = get_response.headers.get("content-type")
encoding = get_response.encoding
page_source = get_response.text
final_url = get_response.url
if "text/html" in content_type and not "<body" in page_source:
print "No <body> tag found in page source. Requesting URL with Selenium: ", final_url
try:
browser.get(final_url)
page_source = browser.page_source
except:
print "First Selenium request failed. Trying one last time."
browser.get(final_url)
page_source = browser.page_source
else:
if "text/html" in content_type and not "<body" in page_source:
print "No <body> tag found in page source. Requesting URL with Selenium one last time."
browser.get(final_url)
page_source = browser.page_source
final_url = browser.current_url
print "Found final URL: %s" % final_url
encoded_data, encoding_used = get_encoded_data(page_source, encoding)
filepath = get_filepath(final_url, encoding_used, output_dir)
with open(filepath, "w") as f:
f.write(encoded_data)
print "Wrote file: %s with encoding: %s" % (filepath, encoding_used)
except:
errors_encountered += 1
failed_urls.append(url)
try:
traceback_info = "\n".join(traceback.format_exception(*(sys.exc_info())))
except:
traceback_info = ""
print "*** ERROR PROCESSING: %s ***\nTraceback: %s\n" % (url, traceback_info)
print "\nOperational Errors: %d\n" % errors_encountered
if failed_urls:
print "The following %d URLs failed:" % len(failed_urls)
for url in failed_urls:
print url