pyzor.digest
Handle digesting the messages.
-
class pyzor.digest.DataDigester(msg, spec=None)[source]
Bases: object
The major workhouse class.
-
atomic_num_lines = 4
-
digest
-
classmethod digest_payloads(msg)[source]
-
email_ptrn = re.compile('\\S+@\\S+')
-
handle_atomic(lines)[source]
We digest everything.
-
handle_line(line)[source]
-
handle_pieced(lines, spec)[source]
Digest stuff according to the spec.
-
longstr_ptrn = re.compile('\\S{10,}')
-
min_line_length = 8
-
classmethod normalize(s)[source]
-
static normalize_html_part(s)[source]
-
classmethod should_handle_line(s)[source]
-
unwanted_txt_repl = ''
-
url_ptrn = re.compile('[a-z]+:\\S+', re.IGNORECASE)
-
value
-
ws_ptrn = re.compile('\\s')
-
class pyzor.digest.HTMLStripper(collector)[source]
Bases: HTMLParser
Strip all tags from the HTML.
-
handle_data(data)[source]
Keep track of the data.
-
handle_endtag(tag)[source]
-
handle_starttag(tag, attrs)[source]
-
class pyzor.digest.PrintingDataDigester(msg, spec=None)[source]
Bases: DataDigester
Extends DataDigester: prints out what we’re digesting.
-
digest
-
handle_line(line)[source]
-
value