MCPcopy
hub / github.com/scrapy/scrapy / _assert_files_downloaded

Method _assert_files_downloaded

tests/test_pipeline_crawl.py:105–126  ·  view source on GitHub ↗
(self, items, logs)

Source from the content-addressed store, hash-verified

103 return crawler
104
105 def _assert_files_downloaded(self, items, logs):
106 assert len(items) == 1
107 assert self.media_key in items[0]
108
109 # check that logs show the expected number of successful file downloads
110 file_dl_success = "File (downloaded): Downloaded file from"
111 assert logs.count(file_dl_success) == 3
112
113 # check that the images/files status is `downloaded`
114 for item in items:
115 for i in item[self.media_key]:
116 assert i["status"] == "downloaded"
117
118 # check that the images/files checksums are what we know they should be
119 if self.expected_checksums is not None:
120 checksums = {i["checksum"] for item in items for i in item[self.media_key]}
121 assert checksums == self.expected_checksums
122
123 # check that the image files where actually written to the media store
124 for item in items:
125 for i in item[self.media_key]:
126 assert (self.tmpmediastore / i["path"]).exists()
127
128 def _assert_files_download_failure(self, crawler, items, code, logs):
129 # check that the item does NOT have the "images/files" field populated

Calls

no outgoing calls

Tested by

no test coverage detected