Skip to content
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

Jump to bottom

Add data_source field to Metadata to differentiate between in-pixel and crawled metadata. #18

Merged
merged 1 commit into from
Mar 7, 2017
Merged

Add data_source field to Metadata to differentiate between in-pixel and crawled metadata. #18

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
11 changes: 8 additions & 3 deletions parsely_raw_data/event.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -82,13 +82,15 @@ class Metadata(SlotsMixin):
__slots__ = ('authors', 'canonical_url', 'urls', 'page_type', 'post_id',
'pub_date_tmsp', 'custom_metadata', 'section', 'tags',
'save_date_tmsp', 'thumb_url', 'title', 'image_url',
'full_content_word_count', 'share_urls', 'duration')
'full_content_word_count', 'share_urls', 'duration',
'data_source')
__version__ = 1

def __init__(self, authors, canonical_url, urls, page_type, post_id,
pub_date_tmsp, custom_metadata, section, tags,
save_date_tmsp, thumb_url, title, image_url,
full_content_word_count, share_urls, duration):
full_content_word_count, share_urls, duration,
data_source):
self.authors = authors
self.canonical_url = canonical_url
self.urls = urls
Expand All @@ -105,6 +107,7 @@ def __init__(self, authors, canonical_url, urls, page_type, post_id,
self.full_content_word_count = full_content_word_count
self.share_urls = share_urls
self.duration = duration
self.data_source = data_source


class SlotInfo(SlotsMixin):
Expand Down Expand Up @@ -285,6 +288,7 @@ def to_dict(self):
event_dict['metadata.full_content_word_count'] = self.metadata.full_content_word_count
event_dict['metadata.share_urls'] = self.metadata.share_urls
event_dict['metadata.duration'] = self.metadata.duration
event_dict['metadata.data_source'] = self.metadata.data_source
event_dict['metadata.__version__'] = self.metadata.__version__
else:
event_dict['metadata'] = False
Expand Down Expand Up @@ -363,7 +367,8 @@ def from_dict(cls, data):
data.get('metadata.image_url'),
data.get('metadata.full_content_word_count'),
data.get('metadata.share_urls'),
data.get('metadata.duration'))
data.get('metadata.duration'),
data.get('metadata.data_source'))
else:
metadata = None
if data.get('campaign'):
Expand Down
5 changes: 3 additions & 2 deletions tests/test_event.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,7 +42,8 @@
"http://parsely.com/imgurl",
420,
["http://twitter.com/nothing"],
69
69,
'crawl'
),
CampaignInfo('spring_sale', 'email', 'newsletter', 'logolink', 'foo'),
EventFlags(False),
Expand All @@ -62,7 +63,7 @@ def test_to_dict_checker():
assert len(SlotInfo.__slots__) == 4, msg
assert len(TimestampInfo.__slots__) == 3, msg
assert len(VisitorInfo.__slots__) == 3, msg
assert len(Metadata.__slots__) == 16, msg
assert len(Metadata.__slots__) == 17, msg
assert len(CampaignInfo.__slots__) == 5, msg
assert len(EventFlags.__slots__) == 1, msg

Expand Down