STRLCPY/maigret

* Fixed BongaCams, links parsing improved

* Fixed tests

Revision indexing in progress... (symbol navigation in revisions will be accurate after indexed)

Total 4 files Show one by one

■ ■ ■ ■ ■ ■

maigret/resources/data.json

		skipped 2143 lines
2144	2144		"cz",
2145	2145		"webcam"
2146	2146		],
2147		-	"checkType": "status_code",
	2147	+	"absenceStrs": [
	2148	+	"<link rel=\"preconnect\""
	2149	+	],
	2150	+	"presenseStrs": [
	2151	+	"<title>Informa\u00e7\u00e3o e p\u00e1gina"
	2152	+	],
	2153	+	"checkType": "message",
2148	2154		"alexaRank": 30,
2149	2155		"urlMain": "https://pt.bongacams.com",
2150	2156		"url": "https://pt.bongacams.com/profile/{username}",
2151		-	"usernameClaimed": "asuna-black",
	2157	+	"usernameClaimed": "Icehotangel",
2152	2158		"usernameUnclaimed": "noonewouldeverusethis77777"
2153	2159		},
2154	2160		"Bookandreader": {
		skipped 10971 lines
13126	13132		"checkType": "response_url",
13127	13133		"alexaRank": 82345,
13128	13134		"urlMain": "http://sprashivai.ru",
13129		-	"url": "http://sprashivai.ru/{username}?sl",
	13135	+	"url": "http://sprashivai.ru/{username}",
13130	13136		"usernameClaimed": "red",
13131	13137		"usernameUnclaimed": "noonewouldeverusethis7"
13132	13138		},
		skipped 15948 lines

■ ■ ■ ■ ■ ■

maigret/utils.py

		skipped 41 lines
42	42
43	43
44	44		class URLMatcher:
45		-	_HTTP_URL_RE_STR = "^https?://(www.)?(.+)$"
	45	+	_HTTP_URL_RE_STR = "^https?://(www.\|m.)?(.+)$"
46	46		HTTP_URL_RE = re.compile(_HTTP_URL_RE_STR)
47	47		UNSAFE_SYMBOLS = ".?"
48	48
		skipped 17 lines
66	66		)
67	67		regexp_str = self._HTTP_URL_RE_STR.replace("(.+)", url_regexp)
68	68
69		-	return re.compile(regexp_str)
	69	+	return re.compile(regexp_str, re.IGNORECASE)
70	70
71	71
72	72		def ascii_data_display(data: str) -> Any:
		skipped 50 lines

■ ■ ■ ■ ■ ■

tests/test_sites.py

		skipped 114 lines
115	115
116	116		assert (
117	117		db.sites[0].url_regexp.pattern
118		-	== r'^https?://(www.)?forum\.amperka\.ru/members/\?username=(.+?)$'
	118	+	== r'^https?://(www.\|m.)?forum\.amperka\.ru/members/\?username=(.+?)$'
119	119		)
120	120		assert (
121	121		db.sites[0].detect_username('http://forum.amperka.ru/members/?username=test')
		skipped 84 lines

■ ■ ■ ■ ■ ■

tests/test_utils.py

		skipped 97 lines
98	98		# ensure all combinations match pattern
99	99		assert (
100	100		URLMatcher.make_profile_url_regexp(url).pattern
101		-	== r'^https?://(www.)?flickr\.com/photos/(.+?)$'
	101	+	== r'^https?://(www.\|m.)?flickr\.com/photos/(.+?)$'
102	102		)
103	103
104	104
		skipped 42 lines