def bot_gen(rev_pages, language, api_url):
session = api.Session(api_url)
extractor = APIExtractor(session, language=language)
for rev_id, page_id in rev_pages:
sys.stderr.write(".")
sys.stderr.flush()
try:
# Detect reverted status
revert = reverts.api.check(session, rev_id, page_id, radius=3)
reverted = revert is not None
added_words = list(
extractor.extract(rev_id, [diff.added_words]))[0]
yield Edit(rev_id, added_words, reverted)
except KeyboardInterrupt:
sys.stderr.write("\n^C Caught. Exiting...")
break
except:
sys.stderr.write(traceback.format_exc())
sys.stderr.write("\n")
sys.stderr.write("\n")
def bot_gen(rev_pages, language, api_url):
session = api.Session(api_url)
extractor = APIExtractor(session, language=language)
for rev_id, page_id in rev_pages:
sys.stderr.write(".")
sys.stderr.flush()
try:
# Detect reverted status
revert = reverts.api.check(session, rev_id, page_id, radius=3)
reverted = revert is not None
added_words = list(extractor.extract(rev_id,
[diff.added_words]))[0]
yield Edit(rev_id, added_words, reverted)
except KeyboardInterrupt:
sys.stderr.write("\n^C Caught. Exiting...")
break
except:
sys.stderr.write(traceback.format_exc())
sys.stderr.write("\n")
sys.stderr.write("\n")
import mwapi
from revscoring import ScorerModel
from revscoring.extractors import APIExtractor
with open("models/enwiki.damaging.linear_svc.model") as f:
scorer_model = ScorerModel.load(f)
extractor = APIExtractor(mwapi.Session(host="https://en.wikipedia.org",
user_agent="revscoring demo"))
feature_values = extractor.extract(123456789, scorer_model.features)
print(scorer_model.score(feature_values))
import mwapi
from revscoring import ScorerModel
from revscoring.extractors import APIExtractor
with open("models/enwiki.damaging.linear_svc.model") as f:
scorer_model = ScorerModel.load(f)
extractor = APIExtractor(
mwapi.Session(host="https://en.wikipedia.org",
user_agent="revscoring demo"))
feature_values = extractor.extract(123456789, scorer_model.features)
print(scorer_model.score(feature_values))
count += 1
else:
break
"""
Feature to examine. Let FEATURE be one of
diff.added_tokens
diff.removed_tokens
diff.added_segments
diff.removed_segments
revision.content
revision.content_tokens
"""
FEATURE = diff.added_segments
# extract data from selected revisions and write to selected file
extr = APIExtractor(mwapi.Session("https://en.wikipedia.org"))
for id in rev_ids:
data = extr.extract(id, FEATURE)
dump_target.write("\n\nBeginning %s of revision %d\n\n" % (FEATURE, id))
if type(data) is str:
dump_target.write(data)
elif type(data) is list:
dump_target.writelines(data)
else:
print("Unknown Type")
exit()
dump_target.write("\n\nEnd %s of revision %d" % (FEATURE, id))
revision.day_of_week, revision.has_custom_comment,
revision.has_section_comment, revision.hour_of_day,
revision.image_links, revision.infobox_templates,
revision.content_chars,
revision.infonoise, revision.internal_links,
revision.level_1_headings,
revision.level_2_headings,
revision.level_3_headings,
revision.level_4_headings,
revision.level_5_headings,
revision.level_6_headings,
revision.markup_chars, revision.misspellings,
revision.numeric_chars, revision.proportion_of_badwords,
revision.proportion_of_markup_chars,
revision.proportion_of_misspellings,
revision.proportion_of_numeric_chars,
revision.proportion_of_symbolic_chars,
revision.proportion_of_templated_references,
revision.proportion_of_uppercase_chars,
revision.ref_tags, revision.symbolic_chars,
revision.templates, revision.uppercase_chars, revision.words,
user.age, user.is_anon, user.is_bot]
print("Extracting {0} features for ".format(len(features)) +
"https://pt.wikipedia.org/w/index.php?diff=4083720")
values = api_extractor.extract(4083720, features)
for feature, value in zip(features, values):
print("{0}: {1}".format(feature, value))
sys.stdout.flush()
from mw.api import Session
from revscoring.extractors import APIExtractor
from revscoring.features import diff, parent_revision, revision, user
api_extractor = APIExtractor(Session("https://en.wikipedia.org/w/api.php"))
features = [revision.day_of_week,
revision.hour_of_day,
revision.has_custom_comment,
diff.bytes_changed,
diff.chars_added,
user.age,
user.is_anon,
user.is_bot]
values = api_extractor.extract(
624577024,
features
)
for feature, value in zip(features, values):
print("{0}: {1}".format(feature, value))
parent_revision.proportion_of_uppercase_chars,
parent_revision.revision_bytes, parent_revision.seconds_since,
parent_revision.symbolic_chars, parent_revision.uppercase_chars,
parent_revision.was_same_user, parent_revision.words,
previous_user_revision.seconds_since, revision.badwords, revision.bytes,
revision.category_links, revision.chars, revision.cite_templates,
revision.day_of_week, revision.has_custom_comment,
revision.has_section_comment, revision.hour_of_day, revision.image_links,
revision.infobox_templates, revision.content_chars, revision.infonoise,
revision.internal_links, revision.level_1_headings,
revision.level_2_headings, revision.level_3_headings,
revision.level_4_headings, revision.level_5_headings,
revision.level_6_headings, revision.markup_chars, revision.misspellings,
revision.numeric_chars, revision.proportion_of_badwords,
revision.proportion_of_markup_chars, revision.proportion_of_misspellings,
revision.proportion_of_numeric_chars,
revision.proportion_of_symbolic_chars,
revision.proportion_of_templated_references,
revision.proportion_of_uppercase_chars, revision.ref_tags,
revision.symbolic_chars, revision.templates, revision.uppercase_chars,
revision.words, user.age, user.is_anon, user.is_bot
]
print("Extracting {0} features for ".format(len(features)) +
"https://pt.wikipedia.org/w/index.php?diff=4083720")
values = api_extractor.extract(4083720, features)
for feature, value in zip(features, values):
print("{0}: {1}".format(feature, value))
sys.stdout.flush()
