Skip to content

[MRG] scrapely.tool: add support for non-ascii <text> and <data> arguments #46

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Oct 10, 2013
Merged

[MRG] scrapely.tool: add support for non-ascii <text> and <data> arguments #46

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f2d780e
scrapely.tool: add support for non-ascii <text> and <data> arguments
kmike Oct 2, 2013
4e43934
fix command-line scrapely.tool usage that was broken by previous commit
kmike Oct 4, 2013
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
31 changes: 17 additions & 14 deletions scrapely/tool.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,21 +43,21 @@ def do_t(self, line):
"""t <template> <text> - test selection text"""
template_id, criteria = line.split(' ', 1)
t = self._load_template(template_id)
criteria = parse_criteria(criteria)
criteria = self._parse_criteria(criteria)
tm = TemplateMaker(t)
selection = apply_criteria(criteria, tm)
for n, i in enumerate(selection):
print "[%d] %r" % (n, remove_annotation(tm.selected_data(i)))

def do_a(self, line):
"""a <template> <data> [-n number] [-f field]- add or test annotation

Add a new annotation (if -f is passed) or test what would be annotated
otherwise
"""
template_id, criteria = line.split(' ', 1)
t = self._load_template(template_id)
criteria = parse_criteria(criteria)
criteria = self._parse_criteria(criteria)
tm = TemplateMaker(t)
selection = apply_criteria(criteria, tm)
if criteria.field:
Expand All @@ -78,7 +78,7 @@ def do_al(self, template_id):
t = self._load_template(template_id)
tm = TemplateMaker(t)
for n, (a, i) in enumerate(tm.annotations()):
print "[%s-%d] (%s) %r" % (template_id, n, a['annotations']['content'],
print "[%s-%d] (%s) %r" % (template_id, n, a['annotations']['content'],
remove_annotation(tm.selected_data(i)))

def do_s(self, url):
Expand Down Expand Up @@ -126,21 +126,24 @@ def _save_templates(self, templates):
with open(self.filename, 'w') as f:
templates = [page_to_dict(t) for t in templates]
return json.dump({'templates': templates}, f)


def _parse_criteria(self, criteria_str):
"""Parse the given criteria string and returns a criteria object"""
p = optparse.OptionParser()
p.add_option('-f', '--field', help='field to annotate')
p.add_option('-n', '--number', type="int", help='number of result to select')
o, a = p.parse_args(shlex.split(criteria_str))

encoding = getattr(self.stdin, 'encoding', None) or sys.stdin.encoding
o.text = ' '.join(a).decode(encoding or 'ascii')
return o


def parse_at(ta_line):
p = optparse.OptionParser()
p.add_option('-e', '--encoding', help='page encoding')
return p.parse_args(shlex.split(ta_line))

def parse_criteria(criteria_str):
"""Parse the given criteria string and returns a criteria object"""
p = optparse.OptionParser()
p.add_option('-f', '--field', help='field to annotate')
p.add_option('-n', '--number', type="int", help='number of result to select')
o, a = p.parse_args(shlex.split(criteria_str))
o.text = ' '.join(a)
return o

def apply_criteria(criteria, tm):
"""Apply the given criteria object to the given template"""
func = best_match(criteria.text) if criteria.text else lambda x, y: False
Expand Down