/usr/lib/python2.7/dist-packages/scrapy/pipelines/files.py is in python-scrapy 1.0.3-2.
This file is owned by root:root, with mode 0o644.
The actual contents of the file can be viewed below.
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 | """
Files Pipeline
See documentation in topics/media-pipeline.rst
"""
import hashlib
import os
import os.path
import rfc822
import time
import logging
from six.moves.urllib.parse import urlparse
from collections import defaultdict
import six
try:
from cStringIO import StringIO as BytesIO
except ImportError:
from io import BytesIO
from twisted.internet import defer, threads
from scrapy.pipelines.media import MediaPipeline
from scrapy.exceptions import NotConfigured, IgnoreRequest
from scrapy.http import Request
from scrapy.utils.misc import md5sum
from scrapy.utils.log import failure_to_exc_info
logger = logging.getLogger(__name__)
class FileException(Exception):
"""General media error exception"""
class FSFilesStore(object):
def __init__(self, basedir):
if '://' in basedir:
basedir = basedir.split('://', 1)[1]
self.basedir = basedir
self._mkdir(self.basedir)
self.created_directories = defaultdict(set)
def persist_file(self, path, buf, info, meta=None, headers=None):
absolute_path = self._get_filesystem_path(path)
self._mkdir(os.path.dirname(absolute_path), info)
with open(absolute_path, 'wb') as f:
f.write(buf.getvalue())
def stat_file(self, path, info):
absolute_path = self._get_filesystem_path(path)
try:
last_modified = os.path.getmtime(absolute_path)
except: # FIXME: catching everything!
return {}
with open(absolute_path, 'rb') as f:
checksum = md5sum(f)
return {'last_modified': last_modified, 'checksum': checksum}
def _get_filesystem_path(self, path):
path_comps = path.split('/')
return os.path.join(self.basedir, *path_comps)
def _mkdir(self, dirname, domain=None):
seen = self.created_directories[domain] if domain else set()
if dirname not in seen:
if not os.path.exists(dirname):
os.makedirs(dirname)
seen.add(dirname)
class S3FilesStore(object):
AWS_ACCESS_KEY_ID = None
AWS_SECRET_ACCESS_KEY = None
POLICY = 'public-read'
HEADERS = {
'Cache-Control': 'max-age=172800',
}
def __init__(self, uri):
assert uri.startswith('s3://')
self.bucket, self.prefix = uri[5:].split('/', 1)
def stat_file(self, path, info):
def _onsuccess(boto_key):
checksum = boto_key.etag.strip('"')
last_modified = boto_key.last_modified
modified_tuple = rfc822.parsedate_tz(last_modified)
modified_stamp = int(rfc822.mktime_tz(modified_tuple))
return {'checksum': checksum, 'last_modified': modified_stamp}
return self._get_boto_key(path).addCallback(_onsuccess)
def _get_boto_bucket(self):
from boto.s3.connection import S3Connection
# disable ssl (is_secure=False) because of this python bug:
# http://bugs.python.org/issue5103
c = S3Connection(self.AWS_ACCESS_KEY_ID, self.AWS_SECRET_ACCESS_KEY, is_secure=False)
return c.get_bucket(self.bucket, validate=False)
def _get_boto_key(self, path):
b = self._get_boto_bucket()
key_name = '%s%s' % (self.prefix, path)
return threads.deferToThread(b.get_key, key_name)
def persist_file(self, path, buf, info, meta=None, headers=None):
"""Upload file to S3 storage"""
b = self._get_boto_bucket()
key_name = '%s%s' % (self.prefix, path)
k = b.new_key(key_name)
if meta:
for metakey, metavalue in six.iteritems(meta):
k.set_metadata(metakey, str(metavalue))
h = self.HEADERS.copy()
if headers:
h.update(headers)
buf.seek(0)
return threads.deferToThread(k.set_contents_from_string, buf.getvalue(),
headers=h, policy=self.POLICY)
class FilesPipeline(MediaPipeline):
"""Abstract pipeline that implement the file downloading
This pipeline tries to minimize network transfers and file processing,
doing stat of the files and determining if file is new, uptodate or
expired.
`new` files are those that pipeline never processed and needs to be
downloaded from supplier site the first time.
`uptodate` files are the ones that the pipeline processed and are still
valid files.
`expired` files are those that pipeline already processed but the last
modification was made long time ago, so a reprocessing is recommended to
refresh it in case of change.
"""
MEDIA_NAME = "file"
EXPIRES = 90
STORE_SCHEMES = {
'': FSFilesStore,
'file': FSFilesStore,
's3': S3FilesStore,
}
DEFAULT_FILES_URLS_FIELD = 'file_urls'
DEFAULT_FILES_RESULT_FIELD = 'files'
def __init__(self, store_uri, download_func=None):
if not store_uri:
raise NotConfigured
self.store = self._get_store(store_uri)
super(FilesPipeline, self).__init__(download_func=download_func)
@classmethod
def from_settings(cls, settings):
s3store = cls.STORE_SCHEMES['s3']
s3store.AWS_ACCESS_KEY_ID = settings['AWS_ACCESS_KEY_ID']
s3store.AWS_SECRET_ACCESS_KEY = settings['AWS_SECRET_ACCESS_KEY']
cls.FILES_URLS_FIELD = settings.get('FILES_URLS_FIELD', cls.DEFAULT_FILES_URLS_FIELD)
cls.FILES_RESULT_FIELD = settings.get('FILES_RESULT_FIELD', cls.DEFAULT_FILES_RESULT_FIELD)
cls.EXPIRES = settings.getint('FILES_EXPIRES', 90)
store_uri = settings['FILES_STORE']
return cls(store_uri)
def _get_store(self, uri):
if os.path.isabs(uri): # to support win32 paths like: C:\\some\dir
scheme = 'file'
else:
scheme = urlparse(uri).scheme
store_cls = self.STORE_SCHEMES[scheme]
return store_cls(uri)
def media_to_download(self, request, info):
def _onsuccess(result):
if not result:
return # returning None force download
last_modified = result.get('last_modified', None)
if not last_modified:
return # returning None force download
age_seconds = time.time() - last_modified
age_days = age_seconds / 60 / 60 / 24
if age_days > self.EXPIRES:
return # returning None force download
referer = request.headers.get('Referer')
logger.debug(
'File (uptodate): Downloaded %(medianame)s from %(request)s '
'referred in <%(referer)s>',
{'medianame': self.MEDIA_NAME, 'request': request,
'referer': referer},
extra={'spider': info.spider}
)
self.inc_stats(info.spider, 'uptodate')
checksum = result.get('checksum', None)
return {'url': request.url, 'path': path, 'checksum': checksum}
path = self.file_path(request, info=info)
dfd = defer.maybeDeferred(self.store.stat_file, path, info)
dfd.addCallbacks(_onsuccess, lambda _: None)
dfd.addErrback(
lambda f:
logger.error(self.__class__.__name__ + '.store.stat_file',
exc_info=failure_to_exc_info(f),
extra={'spider': info.spider})
)
return dfd
def media_failed(self, failure, request, info):
if not isinstance(failure.value, IgnoreRequest):
referer = request.headers.get('Referer')
logger.warning(
'File (unknown-error): Error downloading %(medianame)s from '
'%(request)s referred in <%(referer)s>: %(exception)s',
{'medianame': self.MEDIA_NAME, 'request': request,
'referer': referer, 'exception': failure.value},
extra={'spider': info.spider}
)
raise FileException
def media_downloaded(self, response, request, info):
referer = request.headers.get('Referer')
if response.status != 200:
logger.warning(
'File (code: %(status)s): Error downloading file from '
'%(request)s referred in <%(referer)s>',
{'status': response.status,
'request': request, 'referer': referer},
extra={'spider': info.spider}
)
raise FileException('download-error')
if not response.body:
logger.warning(
'File (empty-content): Empty file from %(request)s referred '
'in <%(referer)s>: no-content',
{'request': request, 'referer': referer},
extra={'spider': info.spider}
)
raise FileException('empty-content')
status = 'cached' if 'cached' in response.flags else 'downloaded'
logger.debug(
'File (%(status)s): Downloaded file from %(request)s referred in '
'<%(referer)s>',
{'status': status, 'request': request, 'referer': referer},
extra={'spider': info.spider}
)
self.inc_stats(info.spider, status)
try:
path = self.file_path(request, response=response, info=info)
checksum = self.file_downloaded(response, request, info)
except FileException as exc:
logger.warning(
'File (error): Error processing file from %(request)s '
'referred in <%(referer)s>: %(errormsg)s',
{'request': request, 'referer': referer, 'errormsg': str(exc)},
extra={'spider': info.spider}, exc_info=True
)
raise
except Exception as exc:
logger.error(
'File (unknown-error): Error processing file from %(request)s '
'referred in <%(referer)s>',
{'request': request, 'referer': referer},
exc_info=True, extra={'spider': info.spider}
)
raise FileException(str(exc))
return {'url': request.url, 'path': path, 'checksum': checksum}
def inc_stats(self, spider, status):
spider.crawler.stats.inc_value('file_count', spider=spider)
spider.crawler.stats.inc_value('file_status_count/%s' % status, spider=spider)
### Overridable Interface
def get_media_requests(self, item, info):
return [Request(x) for x in item.get(self.FILES_URLS_FIELD, [])]
def file_downloaded(self, response, request, info):
path = self.file_path(request, response=response, info=info)
buf = BytesIO(response.body)
self.store.persist_file(path, buf, info)
checksum = md5sum(buf)
return checksum
def item_completed(self, results, item, info):
if isinstance(item, dict) or self.FILES_RESULT_FIELD in item.fields:
item[self.FILES_RESULT_FIELD] = [x for ok, x in results if ok]
return item
def file_path(self, request, response=None, info=None):
## start of deprecation warning block (can be removed in the future)
def _warn():
from scrapy.exceptions import ScrapyDeprecationWarning
import warnings
warnings.warn('FilesPipeline.file_key(url) method is deprecated, please use '
'file_path(request, response=None, info=None) instead',
category=ScrapyDeprecationWarning, stacklevel=1)
# check if called from file_key with url as first argument
if not isinstance(request, Request):
_warn()
url = request
else:
url = request.url
# detect if file_key() method has been overridden
if not hasattr(self.file_key, '_base'):
_warn()
return self.file_key(url)
## end of deprecation warning block
media_guid = hashlib.sha1(url).hexdigest() # change to request.url after deprecation
media_ext = os.path.splitext(url)[1] # change to request.url after deprecation
return 'full/%s%s' % (media_guid, media_ext)
# deprecated
def file_key(self, url):
return self.file_path(url)
file_key._base = True
|