forki 0.2.2 → 0.2.3
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/lib/forki/scrapers/sieves/video_sieves/video_sieve_reel.rb +78 -0
- data/lib/forki/version.rb +1 -1
- metadata +2 -1
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA256:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: f1c8304ed1312aa0e5a7f2f8f5ad2de9a407c761fb7ab9212d66465f599caf6f
|
4
|
+
data.tar.gz: e35a13415b85b9bd57cd9028841c61a324e4011e1a449cd102fe470015ed670d
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: 4179d91435cdc9c82c39c92a15f3df4e7e437f250eccf01e79cf9cb631c326b76badaed3e5851cc26c91713c0cdc27feba56127e8d8c647525960286efd50412
|
7
|
+
data.tar.gz: b5f8ca4461440a785d544017fc1dbc72e9edfdc1d6924717813cf7cd1bfb67fa8695ecc072d00fd476d55eee3ecedca710c107a11bbfe89e8d4b067f443040ae
|
@@ -0,0 +1,78 @@
|
|
1
|
+
class VideoSieveReel < VideoSieve
|
2
|
+
# To check if it's valid for the inputted graphql objects
|
3
|
+
def self.check(graphql_objects)
|
4
|
+
video_object = self.extractor(graphql_objects)
|
5
|
+
|
6
|
+
return false unless video_object.has_key?("short_form_video_context")
|
7
|
+
true
|
8
|
+
rescue StandardError
|
9
|
+
return false
|
10
|
+
end
|
11
|
+
|
12
|
+
# output the expected format of:
|
13
|
+
#
|
14
|
+
# post_details = {
|
15
|
+
# id: video_object["id"],
|
16
|
+
# num_comments: num_comments,
|
17
|
+
# num_shares: share_count_object.fetch("count", nil),
|
18
|
+
# num_views: feedback_object["comet_ufi_summary_and_actions_renderer"]["feedback"]["video_view_count"],
|
19
|
+
# reshare_warning: feedback_object["comet_ufi_summary_and_actions_renderer"]["feedback"]["should_show_reshare_warning"],
|
20
|
+
# video_preview_image_url: video_object["preferred_thumbnail"]["image"]["uri"],
|
21
|
+
# video_url: video_object["browser_native_hd_url"] || video_object["browser_native_sd_url"],
|
22
|
+
# text: text,
|
23
|
+
# created_at: creation_date,
|
24
|
+
# profile_link: story_node_object["comet_sections"]["context_layout"]["story"]["comet_sections"]["actor_photo"]["story"]["actors"][0]["url"],
|
25
|
+
# has_video: true
|
26
|
+
# }
|
27
|
+
# post_details[:video_preview_image_file] = Forki.retrieve_media(post_details[:video_preview_image_url])
|
28
|
+
# post_details[:video_file] = Forki.retrieve_media(post_details[:video_url])
|
29
|
+
# post_details[:reactions] = reaction_counts
|
30
|
+
|
31
|
+
def self.sieve(graphql_objects)
|
32
|
+
video_object = self.extractor(graphql_objects)
|
33
|
+
|
34
|
+
|
35
|
+
feedback_object = graphql_objects.filter do |go|
|
36
|
+
go = go.first if go.kind_of?(Array) && !go.empty?
|
37
|
+
!go.dig("feedback", "top_level_comments").nil?
|
38
|
+
end.first
|
39
|
+
|
40
|
+
reels_feedback_renderer = graphql_objects.filter do |go|
|
41
|
+
go.dig("reels_feedback_renderer")
|
42
|
+
end.first
|
43
|
+
|
44
|
+
reels_feedback_renderer["reels_feedback_renderer"]["story"]
|
45
|
+
reshare_warning = video_object["short_form_video_context"]["playback_video"].dig("warning_screen_renderer", "cix_screen", "view_model", "__typename") == "OverlayWarningScreenViewModel"
|
46
|
+
|
47
|
+
video_preview_image_url = video_object["short_form_video_context"]["playback_video"]["preferred_thumbnail"]["image"]["uri"]
|
48
|
+
video_url = video_object["short_form_video_context"]["playback_video"]["browser_native_hd_url"] || video_object["short_form_video_context"]["playback_video"]["browser_native_sd_url"]
|
49
|
+
|
50
|
+
post_details = {
|
51
|
+
id: video_object["short_form_video_context"]["video"]["id"],
|
52
|
+
num_comments: feedback_object["feedback"]["top_level_comments"]["totalCountIncludingReplies"],
|
53
|
+
num_shared: Forki::Scraper.extract_int_from_num_element(feedback_object["feedback"]["share_count_reduced"]),
|
54
|
+
num_views: nil,
|
55
|
+
reshare_warning: reshare_warning,
|
56
|
+
video_preview_image_url: video_preview_image_url,
|
57
|
+
video_url: video_url,
|
58
|
+
text: nil, # Reels don't have text
|
59
|
+
created_at: JSON.parse(feedback_object["tracking"])["page_insights"].first[1]["post_context"]["publish_time"], # Yea, this is weird
|
60
|
+
profile_link: video_object["short_form_video_context"]["video_owner"]["url"],
|
61
|
+
has_video: true,
|
62
|
+
video_preview_image_file: Forki.retrieve_media(video_preview_image_url),
|
63
|
+
video_file: Forki.retrieve_media(video_url),
|
64
|
+
reactions: nil # Only available on comments it seems? Look into this again sometime
|
65
|
+
}
|
66
|
+
end
|
67
|
+
|
68
|
+
private
|
69
|
+
|
70
|
+
def self.extractor(graphql_objects)
|
71
|
+
video_objects = graphql_objects.filter do |go|
|
72
|
+
go = go.first if go.kind_of?(Array) && !go.empty?
|
73
|
+
go.has_key?("video")
|
74
|
+
end
|
75
|
+
|
76
|
+
video_objects.first.dig("video", "creation_story")
|
77
|
+
end
|
78
|
+
end
|
data/lib/forki/version.rb
CHANGED
metadata
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: forki
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.2.
|
4
|
+
version: 0.2.3
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- ''
|
@@ -126,6 +126,7 @@ files:
|
|
126
126
|
- lib/forki/scrapers/scraper.rb
|
127
127
|
- lib/forki/scrapers/sieves/image_sieves/image_sieve.rb.rb
|
128
128
|
- lib/forki/scrapers/sieves/video_sieves/video_sieve.rb
|
129
|
+
- lib/forki/scrapers/sieves/video_sieves/video_sieve_reel.rb
|
129
130
|
- lib/forki/scrapers/sieves/video_sieves/video_sieve_video_page.rb
|
130
131
|
- lib/forki/scrapers/sieves/video_sieves/video_sieve_watch_tab.rb
|
131
132
|
- lib/forki/scrapers/user_scraper.rb
|