Refactoring.
This commit is contained in:
parent
23e1147370
commit
3ed43f036d
|
|
@ -24,7 +24,9 @@ import requests
|
|||
from time import sleep
|
||||
from random import randint
|
||||
from datetime import datetime, timezone
|
||||
from ExtensionCrawler.config import *
|
||||
from ExtensionCrawler.util import *
|
||||
from ExtensionCrawler.archive import *
|
||||
import dateutil
|
||||
import dateutil.parser
|
||||
|
||||
|
|
@ -161,3 +163,178 @@ def last_crx(dir, extid):
|
|||
return last_archive
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
def update_overview(dir, verbose, ext_id):
|
||||
log(verbose, " * overview page: ")
|
||||
try:
|
||||
res = requests.get(const_overview_url(ext_id))
|
||||
log(verbose, "{}".format(str(res.status_code)))
|
||||
store_request_text(dir, 'overview.html', res)
|
||||
except Exception as e:
|
||||
log(verbose, " / Exception: {}\n".format(str(e)))
|
||||
write_text(dir, 'overview.html.exception', str(e))
|
||||
return RequestResult(res, e)
|
||||
log(verbose, "\n")
|
||||
return RequestResult(res)
|
||||
|
||||
|
||||
def validate_crx_response(res, extfilename):
|
||||
regex_extfilename = re.compile(r'^extension[_0-9]+\.crx$')
|
||||
if not 'Content-Type' in res.headers:
|
||||
raise CrawlError(extid, 'Did not find Content-Type header.',
|
||||
'\n'.join(res.iter_lines()))
|
||||
if not res.headers['Content-Type'] == 'application/x-chrome-extension':
|
||||
text = [line.decode('utf-8') for line in res.iter_lines()]
|
||||
raise CrawlError(
|
||||
extid,
|
||||
'Expected Content-Type header to be application/x-chrome-extension, but got {}.'.
|
||||
format(res.headers['Content-Type']), '\n'.join(text))
|
||||
if not regex_extfilename.match(extfilename):
|
||||
raise CrawlError(
|
||||
extid, '{} is not a valid extension file name, skipping...'.format(
|
||||
extfilename))
|
||||
|
||||
|
||||
def update_crx(dir, verbose, ext_id):
|
||||
last_crx_file = last_crx(dir, ext_id)
|
||||
last_crx_http_date = last_modified_http_date(last_crx_file)
|
||||
log(verbose, " * crx archive (Last: {}): ".format(
|
||||
valueOf(last_crx_http_date, "n/a")))
|
||||
headers = ""
|
||||
if last_crx_file is not "":
|
||||
headers = {'If-Modified-Since': last_crx_http_date}
|
||||
try:
|
||||
res = requests.get(
|
||||
const_download_url().format(ext_id),
|
||||
stream=True,
|
||||
headers=headers)
|
||||
log(verbose, "{}".format(str(res.status_code)))
|
||||
extfilename = os.path.basename(res.url)
|
||||
store_request_metadata(dir, extfilename, res)
|
||||
|
||||
if res.status_code == 304:
|
||||
write_text(dir, extfilename + ".link",
|
||||
os.path.join("..",
|
||||
last_modified_utc_date(last_crx_file),
|
||||
extfilename) + "\n")
|
||||
else:
|
||||
validate_crx_response(res, extfilename)
|
||||
with open(os.path.join(dir, extfilename), 'wb') as f:
|
||||
for chunk in res.iter_content(chunk_size=512 * 1024):
|
||||
if chunk: # filter out keep-alive new chunks
|
||||
f.write(chunk)
|
||||
except Exception as e:
|
||||
log(verbose, " / Exception: {}\n".format(str(e)))
|
||||
write_text(dir, extfilename + ".exception", str(e))
|
||||
return RequestResult(res, e)
|
||||
log(verbose, "\n")
|
||||
return RequestResult(res)
|
||||
|
||||
|
||||
def update_reviews(dir, verbose, ext_id):
|
||||
log(verbose, " * review page: ")
|
||||
res = None
|
||||
try:
|
||||
google_dos_protection()
|
||||
res = requests.post(
|
||||
const_review_url(),
|
||||
data=const_review_payload(ext_id, "0",
|
||||
"100"))
|
||||
log(verbose, "{}/".format(str(res.status_code)))
|
||||
store_request_text(dir, 'reviews000-099.text', res)
|
||||
google_dos_protection()
|
||||
res = requests.post(
|
||||
const_review_url(),
|
||||
data=const_review_payload(ext_id, "0",
|
||||
"100"))
|
||||
log(verbose, "{}".format(str(res.status_code)))
|
||||
store_request_text(dir, 'reviews100-199.text', res)
|
||||
except Exception as e:
|
||||
log(verbose, " / Exception: {}\n".format(str(e)))
|
||||
write_text(dir, 'reviews.html.exception', str(e))
|
||||
return RequestResult(res, e)
|
||||
log(verbose, "\n")
|
||||
return RequestResult(res)
|
||||
|
||||
|
||||
def update_support(dir, verbose, ext_id):
|
||||
log(verbose, " * support page: ")
|
||||
res = None
|
||||
try:
|
||||
google_dos_protection()
|
||||
res = requests.post(
|
||||
const_support_url(),
|
||||
data=const_support_payload(ext_id, "0",
|
||||
"100"))
|
||||
log(verbose, "{}/".format(str(res.status_code)))
|
||||
store_request_text(dir, 'support000-099.text', res)
|
||||
google_dos_protection()
|
||||
res = requests.post(
|
||||
const_support_url(),
|
||||
data=const_support_payload(ext_id, "100",
|
||||
"100"))
|
||||
log(verbose, "{}".format(str(res.status_code)))
|
||||
store_request_text(dir, 'support100-199.text', res)
|
||||
except Exception as e:
|
||||
log(verbose, " / Exception: {}\n".format(str(e)))
|
||||
write_text(dir, 'support.html.exception', str(e))
|
||||
return RequestResult(res, e)
|
||||
log(verbose, "\n")
|
||||
return RequestResult(res)
|
||||
|
||||
|
||||
def update_extension(archivedir, verbose, forums, ext_id):
|
||||
log(verbose, " Updating {}".format(ext_id))
|
||||
if forums:
|
||||
log(verbose, " (including forums)")
|
||||
log(verbose, "\n")
|
||||
date = datetime.now(timezone.utc).isoformat()
|
||||
dir = os.path.join(
|
||||
os.path.join(archivedir,
|
||||
get_local_archive_dir(ext_id)),
|
||||
date)
|
||||
os.makedirs(dir, exist_ok=True)
|
||||
res_overview = update_overview(dir, verbose, ext_id)
|
||||
res_crx = update_crx(dir, verbose, ext_id)
|
||||
res_reviews = None
|
||||
res_support = None
|
||||
if forums:
|
||||
res_reviews = update_reviews(dir, verbose, ext_id)
|
||||
res_support = update_support(dir, verbose, ext_id)
|
||||
return UpdateResult(ext_id, res_overview, res_crx, res_reviews,
|
||||
res_support)
|
||||
|
||||
|
||||
def update_extensions(archivedir, verbose, forums_ext_ids, known_ext_ids,
|
||||
new_ext_ids):
|
||||
def update_forums(ext_id):
|
||||
return (ext_id in forums_ext_ids)
|
||||
|
||||
ext_ids = known_ext_ids + new_ext_ids
|
||||
log(verbose,
|
||||
"Updating {} extensions ({} new, {} including forums)\n".format(
|
||||
len(ext_ids), len(new_ext_ids), len(forums_ext_ids)))
|
||||
return list(map(lambda ext_id: update_extension(archivedir, verbose,
|
||||
update_forums(ext_id), ext_id),
|
||||
ext_ids))
|
||||
|
||||
|
||||
def get_existing_ids(archivedir, verbose):
|
||||
byte = '[0-9a-z][0-9a-z][0-9a-z][0-9a-z][0-9a-z][0-9a-z][0-9a-z][0-9a-z]'
|
||||
word = byte + byte + byte + byte
|
||||
return list(
|
||||
map(lambda d: re.sub("^.*\/", "", d),
|
||||
glob.glob(os.path.join(archivedir, "*", word))))
|
||||
|
||||
|
||||
def get_forum_ext_ids(confdir, verbose):
|
||||
with open(os.path.join(confdir, "forums.conf")) as f:
|
||||
ids = f.readlines()
|
||||
ids = [x.strip() for x in ids]
|
||||
return ids
|
||||
|
||||
|
||||
|
||||
|
|
|
|||
|
|
@ -22,6 +22,8 @@ import requests
|
|||
import re
|
||||
from functools import reduce
|
||||
import ExtensionCrawler.config
|
||||
from ExtensionCrawler.util import *
|
||||
|
||||
|
||||
def crawl_nearly_all_of_ext_ids():
|
||||
def get_inner_elems(doc):
|
||||
|
|
@ -45,3 +47,12 @@ def crawl_nearly_all_of_ext_ids():
|
|||
lambda x, y: x + y,
|
||||
map(lambda s: [elem.text for elem in get_inner_elems(s)], shards), [])
|
||||
return [re.search("[a-z]{32}", url).group(0) for url in overview_urls]
|
||||
|
||||
def get_new_ids(verbose, known_ids):
|
||||
log(verbose, "Discovering new ids ... \n")
|
||||
discovered_ids = ExtensionCrawler.discover.crawl_nearly_all_of_ext_ids()
|
||||
new_ids = list(set(discovered_ids) - set(known_ids))
|
||||
log(verbose, " Discovered {} new extensions (out of {})\n".format(
|
||||
len(new_ids), len(discovered_ids)))
|
||||
return new_ids
|
||||
|
||||
|
|
|
|||
183
crawler
183
crawler
|
|
@ -27,190 +27,11 @@ from datetime import datetime, timezone
|
|||
from ExtensionCrawler.discover import *
|
||||
from ExtensionCrawler.archive import *
|
||||
from ExtensionCrawler.util import *
|
||||
from ExtensionCrawler.discover import *
|
||||
import dateutil
|
||||
import dateutil.parser
|
||||
|
||||
|
||||
|
||||
def update_overview(dir, verbose, ext_id):
|
||||
log(verbose, " * overview page: ")
|
||||
try:
|
||||
res = requests.get(ExtensionCrawler.config.const_overview_url(ext_id))
|
||||
log(verbose, "{}".format(str(res.status_code)))
|
||||
store_request_text(dir, 'overview.html', res)
|
||||
except Exception as e:
|
||||
log(verbose, " / Exception: {}\n".format(str(e)))
|
||||
write_text(dir, 'overview.html.exception', str(e))
|
||||
return RequestResult(res, e)
|
||||
log(verbose, "\n")
|
||||
return RequestResult(res)
|
||||
|
||||
|
||||
def validate_crx_response(res, extfilename):
|
||||
regex_extfilename = re.compile(r'^extension[_0-9]+\.crx$')
|
||||
if not 'Content-Type' in res.headers:
|
||||
raise CrawlError(extid, 'Did not find Content-Type header.',
|
||||
'\n'.join(res.iter_lines()))
|
||||
if not res.headers['Content-Type'] == 'application/x-chrome-extension':
|
||||
text = [line.decode('utf-8') for line in res.iter_lines()]
|
||||
raise CrawlError(
|
||||
extid,
|
||||
'Expected Content-Type header to be application/x-chrome-extension, but got {}.'.
|
||||
format(res.headers['Content-Type']), '\n'.join(text))
|
||||
if not regex_extfilename.match(extfilename):
|
||||
raise CrawlError(
|
||||
extid, '{} is not a valid extension file name, skipping...'.format(
|
||||
extfilename))
|
||||
|
||||
|
||||
def update_crx(dir, verbose, ext_id):
|
||||
last_crx_file = last_crx(dir, ext_id)
|
||||
last_crx_http_date = last_modified_http_date(last_crx_file)
|
||||
log(verbose, " * crx archive (Last: {}): ".format(
|
||||
valueOf(last_crx_http_date, "n/a")))
|
||||
headers = ""
|
||||
if last_crx_file is not "":
|
||||
headers = {'If-Modified-Since': last_crx_http_date}
|
||||
try:
|
||||
res = requests.get(
|
||||
ExtensionCrawler.config.const_download_url().format(ext_id),
|
||||
stream=True,
|
||||
headers=headers)
|
||||
log(verbose, "{}".format(str(res.status_code)))
|
||||
extfilename = os.path.basename(res.url)
|
||||
store_request_metadata(dir, extfilename, res)
|
||||
|
||||
if res.status_code == 304:
|
||||
write_text(dir, extfilename + ".link",
|
||||
os.path.join("..",
|
||||
last_modified_utc_date(last_crx_file),
|
||||
extfilename) + "\n")
|
||||
else:
|
||||
validate_crx_response(res, extfilename)
|
||||
with open(os.path.join(dir, extfilename), 'wb') as f:
|
||||
for chunk in res.iter_content(chunk_size=512 * 1024):
|
||||
if chunk: # filter out keep-alive new chunks
|
||||
f.write(chunk)
|
||||
except Exception as e:
|
||||
log(verbose, " / Exception: {}\n".format(str(e)))
|
||||
write_text(dir, extfilename + ".exception", str(e))
|
||||
return RequestResult(res, e)
|
||||
log(verbose, "\n")
|
||||
return RequestResult(res)
|
||||
|
||||
|
||||
def update_reviews(dir, verbose, ext_id):
|
||||
log(verbose, " * review page: ")
|
||||
res = None
|
||||
try:
|
||||
google_dos_protection()
|
||||
res = requests.post(
|
||||
ExtensionCrawler.config.const_review_url(),
|
||||
data=ExtensionCrawler.config.const_review_payload(ext_id, "0",
|
||||
"100"))
|
||||
log(verbose, "{}/".format(str(res.status_code)))
|
||||
store_request_text(dir, 'reviews000-099.text', res)
|
||||
google_dos_protection()
|
||||
res = requests.post(
|
||||
ExtensionCrawler.config.const_review_url(),
|
||||
data=ExtensionCrawler.config.const_review_payload(ext_id, "0",
|
||||
"100"))
|
||||
log(verbose, "{}".format(str(res.status_code)))
|
||||
store_request_text(dir, 'reviews100-199.text', res)
|
||||
except Exception as e:
|
||||
log(verbose, " / Exception: {}\n".format(str(e)))
|
||||
write_text(dir, 'reviews.html.exception', str(e))
|
||||
return RequestResult(res, e)
|
||||
log(verbose, "\n")
|
||||
return RequestResult(res)
|
||||
|
||||
|
||||
def update_support(dir, verbose, ext_id):
|
||||
log(verbose, " * support page: ")
|
||||
res = None
|
||||
try:
|
||||
google_dos_protection()
|
||||
res = requests.post(
|
||||
ExtensionCrawler.config.const_support_url(),
|
||||
data=ExtensionCrawler.config.const_support_payload(ext_id, "0",
|
||||
"100"))
|
||||
log(verbose, "{}/".format(str(res.status_code)))
|
||||
store_request_text(dir, 'support000-099.text', res)
|
||||
google_dos_protection()
|
||||
res = requests.post(
|
||||
ExtensionCrawler.config.const_support_url(),
|
||||
data=ExtensionCrawler.config.const_support_payload(ext_id, "100",
|
||||
"100"))
|
||||
log(verbose, "{}".format(str(res.status_code)))
|
||||
store_request_text(dir, 'support100-199.text', res)
|
||||
except Exception as e:
|
||||
log(verbose, " / Exception: {}\n".format(str(e)))
|
||||
write_text(dir, 'support.html.exception', str(e))
|
||||
return RequestResult(res, e)
|
||||
log(verbose, "\n")
|
||||
return RequestResult(res)
|
||||
|
||||
|
||||
def update_extension(archivedir, verbose, forums, ext_id):
|
||||
log(verbose, " Updating {}".format(ext_id))
|
||||
if forums:
|
||||
log(verbose, " (including forums)")
|
||||
log(verbose, "\n")
|
||||
date = datetime.now(timezone.utc).isoformat()
|
||||
dir = os.path.join(
|
||||
os.path.join(archivedir,
|
||||
ExtensionCrawler.archive.get_local_archive_dir(ext_id)),
|
||||
date)
|
||||
os.makedirs(dir, exist_ok=True)
|
||||
res_overview = update_overview(dir, verbose, ext_id)
|
||||
res_crx = update_crx(dir, verbose, ext_id)
|
||||
res_reviews = None
|
||||
res_support = None
|
||||
if forums:
|
||||
res_reviews = update_reviews(dir, verbose, ext_id)
|
||||
res_support = update_support(dir, verbose, ext_id)
|
||||
return UpdateResult(ext_id, res_overview, res_crx, res_reviews,
|
||||
res_support)
|
||||
|
||||
|
||||
def update_extensions(archivedir, verbose, forums_ext_ids, known_ext_ids,
|
||||
new_ext_ids):
|
||||
def update_forums(ext_id):
|
||||
return (ext_id in forums_ext_ids)
|
||||
|
||||
ext_ids = known_ext_ids + new_ext_ids
|
||||
log(verbose,
|
||||
"Updating {} extensions ({} new, {} including forums)\n".format(
|
||||
len(ext_ids), len(new_ext_ids), len(forums_ext_ids)))
|
||||
return list(map(lambda ext_id: update_extension(archivedir, verbose,
|
||||
update_forums(ext_id), ext_id),
|
||||
ext_ids))
|
||||
|
||||
|
||||
def get_existing_ids(archivedir, verbose):
|
||||
byte = '[0-9a-z][0-9a-z][0-9a-z][0-9a-z][0-9a-z][0-9a-z][0-9a-z][0-9a-z]'
|
||||
word = byte + byte + byte + byte
|
||||
return list(
|
||||
map(lambda d: re.sub("^.*\/", "", d),
|
||||
glob.glob(os.path.join(archivedir, "*", word))))
|
||||
|
||||
|
||||
def get_forum_ext_ids(confdir, verbose):
|
||||
with open(os.path.join(confdir, "forums.conf")) as f:
|
||||
ids = f.readlines()
|
||||
ids = [x.strip() for x in ids]
|
||||
return ids
|
||||
|
||||
|
||||
def get_new_ids(verbose, known_ids):
|
||||
log(verbose, "Discovering new ids ... \n")
|
||||
discovered_ids = ExtensionCrawler.discover.crawl_nearly_all_of_ext_ids()
|
||||
new_ids = list(set(discovered_ids) - set(known_ids))
|
||||
log(verbose, " Discovered {} new extensions (out of {})\n".format(
|
||||
len(new_ids), len(discovered_ids)))
|
||||
return new_ids
|
||||
|
||||
|
||||
def log_summary(verbose, res):
|
||||
total = len(res)
|
||||
success = len(list(filter(lambda x: x.is_ok(), res)))
|
||||
|
|
@ -225,7 +46,7 @@ def log_summary(verbose, res):
|
|||
str(success), str(total)))
|
||||
log(verbose, " Not authorized: {}\n".format(str(not_authorized)))
|
||||
log(verbose, " Raised Google DDOS: {}\n".format(str(raised_ddos)))
|
||||
log(verbose, " Updated archives: {}\n".format(str(success-not_modified)))
|
||||
log(verbose, " Not modified archives: {}\n".format(str(not_modified)))
|
||||
log(verbose, " Extensions not in store: {}\n".format(str(not_in_store)))
|
||||
log(verbose, " Unknown exception: {}\n".format(str(has_exception)))
|
||||
|
||||
|
|
|
|||
Loading…
Reference in New Issue