modis-crawler-utils 0.2.71__tar.gz → 0.2.73__tar.gz
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/PKG-INFO +1 -1
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/files.py +2 -2
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/pyproject.toml +1 -1
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/README.md +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/__init__.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/cloudflare_captcha_bypass.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/credentials/__init__.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/credentials/credential.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/credentials/manager.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/credentials/store/__init__.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/credentials/store/local.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/credentials/store/talisman.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/deploy/__init__.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/deploy/bump_version.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/deploy/create_egg.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/deploy/make_arguments_md_file.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/domains.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/echo.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/elasticsearch/__init__.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/elasticsearch/dupefilter.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/elasticsearch/dupefilter_strategies/__init__.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/elasticsearch/dupefilter_strategies/delta_fetch_items.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/elasticsearch/dupefilter_strategies/depth_based.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/elasticsearch/dupefilter_strategies/drop_unproductive_requests.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/elasticsearch/items_pipeline.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/elasticsearch/request_fingerprint.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/elasticsearch/requests_middleware.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/elasticsearch/storage.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/images.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/kafka.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/logstash.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/mongodb.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/proxypy.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/social_media/__init__.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/social_media/items.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/socks.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/splash_proxy.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/states/__init__.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/states/local_store.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/states/talisman_states_api.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/talisman_controller.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/talisman_job_env.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/talisman_proxy.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/talisman_spider_state.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/timestamp.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/trust_level.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/uuid.py +0 -0
- {modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/validate_input.py +0 -0
|
@@ -45,7 +45,7 @@ class FilesPipeline(ImagesPipelineBase, FilesPipelineBase):
|
|
|
45
45
|
|
|
46
46
|
FILES_DENY_ATTACHMENT_TYPES
|
|
47
47
|
Crawl all attachments but these types.
|
|
48
|
-
Default is empty (allow all types).
|
|
48
|
+
Default is "image". This will change to empty (allow all types) when ImagesPipeline will be removed.
|
|
49
49
|
|
|
50
50
|
Attachments without types are always downloaded.
|
|
51
51
|
|
|
@@ -148,7 +148,7 @@ class FilesPipeline(ImagesPipelineBase, FilesPipelineBase):
|
|
|
148
148
|
MAX_PATH_LENGTH = None
|
|
149
149
|
|
|
150
150
|
ALLOW_ATTACHMENT_TYPES = ()
|
|
151
|
-
DENY_ATTACHMENT_TYPES = ()
|
|
151
|
+
DENY_ATTACHMENT_TYPES = ('image',)
|
|
152
152
|
|
|
153
153
|
DEFAULT_FILES_RESULT_FIELD = '_attachments'
|
|
154
154
|
|
|
File without changes
|
|
File without changes
|
{modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/cloudflare_captcha_bypass.py
RENAMED
|
File without changes
|
{modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/credentials/__init__.py
RENAMED
|
File without changes
|
{modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/credentials/credential.py
RENAMED
|
File without changes
|
{modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/credentials/manager.py
RENAMED
|
File without changes
|
|
File without changes
|
{modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/credentials/store/local.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
{modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/deploy/bump_version.py
RENAMED
|
File without changes
|
{modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/deploy/create_egg.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/elasticsearch/__init__.py
RENAMED
|
File without changes
|
{modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/elasticsearch/dupefilter.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/elasticsearch/storage.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/social_media/__init__.py
RENAMED
|
File without changes
|
{modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/social_media/items.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
{modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/states/local_store.py
RENAMED
|
File without changes
|
|
File without changes
|
{modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/talisman_controller.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
{modis_crawler_utils-0.2.71 → modis_crawler_utils-0.2.73}/crawler_utils/talisman_spider_state.py
RENAMED
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|
|
File without changes
|