facebook_scrapper 0.2.0 → 0.2.5
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/facebook_scrapper/scrapper.rb +12 -16
- data/lib/facebook_scrapper/version.rb +1 -1
- metadata +1 -1
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA256:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 47eff0e332eee397e4315689bbaa12761e963bfdefcf00259c990615a7eeebd7
|
|
4
|
+
data.tar.gz: d7da1d1b8c17f07828c0b69884de95e1742b82b2a8859ef4bb280d16df1494c1
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 8ecbe62da7af65a0b4a8b53fae1c9d1220d6d781571500188d6a9d01a5e7d355d7c84b8f1e1c1b7c72dff08fdf2c72b1192b8052353c9bae8c3b22e2e6a40bbf
|
|
7
|
+
data.tar.gz: 0c7f7eb171bb65b3a3bd2b3802a48453026aea4537ed4737c990a4a27ebae7507093a314bd5041bcbe1654ae4ac07d3d57cd126a0642bbef1facf6c2c3f458c9
|
|
@@ -6,20 +6,6 @@ module FacebookScrapper
|
|
|
6
6
|
@driver = Selenium::WebDriver.for :chrome
|
|
7
7
|
end
|
|
8
8
|
|
|
9
|
-
def toBasicUrl(url)
|
|
10
|
-
if url.include? "m.facebook.com"
|
|
11
|
-
return url.gsub!("m.facebook.com", "mbasic.facebook.com")
|
|
12
|
-
elsif url.include? "www.facebook.com"
|
|
13
|
-
return url.gsub!("www.facebook.com", "mbasic.facebook.com")
|
|
14
|
-
else
|
|
15
|
-
return url
|
|
16
|
-
end
|
|
17
|
-
end
|
|
18
|
-
|
|
19
|
-
def get(url)
|
|
20
|
-
@driver.get(toBasicUrl(url))
|
|
21
|
-
end
|
|
22
|
-
|
|
23
9
|
def login(email, password)
|
|
24
10
|
url = "https://mbasic.facebook.com"
|
|
25
11
|
get(url)
|
|
@@ -68,11 +54,11 @@ module FacebookScrapper
|
|
|
68
54
|
get(url)
|
|
69
55
|
posts = []
|
|
70
56
|
all_posts = @driver.find_element(id: "m_group_stories_container").find_elements(css: "div[role='article']")
|
|
71
|
-
puts "Found #{all_posts.length} posts"
|
|
72
57
|
all_posts.each do |raw_post|
|
|
73
58
|
new_post = get_post_object(raw_post, keywords)
|
|
74
59
|
posts.push(new_post) if new_post
|
|
75
60
|
end
|
|
61
|
+
puts "Found #{posts.length} posts"
|
|
76
62
|
return posts
|
|
77
63
|
end
|
|
78
64
|
|
|
@@ -80,11 +66,11 @@ module FacebookScrapper
|
|
|
80
66
|
get("https://mbasic.facebook.com")
|
|
81
67
|
posts = []
|
|
82
68
|
all_posts = @driver.find_elements(css: "div[role='article']")
|
|
83
|
-
puts "Found #{all_posts.length} posts"
|
|
84
69
|
all_posts.each do |raw_post|
|
|
85
70
|
new_post = get_post_object(raw_post, keywords)
|
|
86
71
|
posts.push(new_post) if new_post
|
|
87
72
|
end
|
|
73
|
+
puts "Found #{posts.length} posts"
|
|
88
74
|
return posts
|
|
89
75
|
end
|
|
90
76
|
|
|
@@ -104,6 +90,16 @@ module FacebookScrapper
|
|
|
104
90
|
|
|
105
91
|
private
|
|
106
92
|
|
|
93
|
+
def toBasicUrl(url)
|
|
94
|
+
if url.include? "m.facebook.com"
|
|
95
|
+
return url.gsub!("m.facebook.com", "mbasic.facebook.com")
|
|
96
|
+
elsif url.include? "www.facebook.com"
|
|
97
|
+
return url.gsub!("www.facebook.com", "mbasic.facebook.com")
|
|
98
|
+
else
|
|
99
|
+
return url
|
|
100
|
+
end
|
|
101
|
+
end
|
|
102
|
+
|
|
107
103
|
def get_post_object(raw_post, keywords = [])
|
|
108
104
|
begin
|
|
109
105
|
new_post = raw_post.find_element(css: "div[role='article']")
|