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

#22 Add publisher and venue as columns to dataframe #29

Merged
merged 1 commit into from
Sep 10, 2022
Merged

#22 Add publisher and venue as columns to dataframe #29

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
20 changes: 16 additions & 4 deletions sortgs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -202,6 +202,8 @@ def main():
citations = []
year = []
author = []
venue = []
publisher = []
rank = [0]

# Get content from number_of_results URLs
Expand All @@ -225,10 +227,10 @@ def main():
print(e)

# Create parser
soup = BeautifulSoup(c, 'html.parser')
soup = BeautifulSoup(c, 'html.parser', from_encoding='utf-8')

# Get stuff
mydivs = soup.findAll("div", { "class" : "gs_r" })
mydivs = soup.findAll("div", { "class" : "gs_or" })

for div in mydivs:
try:
Expand Down Expand Up @@ -258,14 +260,24 @@ def main():
except:
author.append("Author not found")

try:
publisher.append(div.find('div',{'class' : 'gs_a'}).text.split("-")[-1])
except:
publisher.append("Publisher not found")

try:
venue.append(" ".join(div.find('div',{'class' : 'gs_a'}).text.split("-")[-2].split(",")[:-1]))
except:
venue.append("Venue not fount")

rank.append(rank[-1]+1)

# Delay
sleep(0.5)

# Create a dataset and sort by the number of citations
data = pd.DataFrame(list(zip(author, title, citations, year, links)), index = rank[1:],
columns=['Author', 'Title', 'Citations', 'Year', 'Source'])
data = pd.DataFrame(list(zip(author, title, citations, year, publisher, venue, links)), index = rank[1:],
columns=['Author', 'Title', 'Citations', 'Year', 'Publisher', 'Venue', 'Source'])
data.index.name = 'Rank'

# Add columns with number of citations per year
Expand Down
8 changes: 4 additions & 4 deletions test/test_sortgs.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,10 +18,10 @@ def setUpClass(self):
self.df_top_sorted_cit_per_year=pd.read_csv('machine_learning.csv')

def test_get_10_results(self):
self.assertEqual(len(self.df_top_10), 12) # Two extra unwanted elements were captured
self.assertEqual(len(self.df_top_10), 10)

def test_get_20_results(self):
self.assertEqual(len(self.df_top_20), 23) # Three extra unwanted elements were captured
self.assertEqual(len(self.df_top_20), 20)

def test_is_sorted(self):
df=self.df_top_20
Expand All @@ -34,15 +34,15 @@ def test_top_result(self):
top_citation = int(df.Citations.values[0])
top_cit_per_year = int(df['cit/year'].values[0])
top_results = [top_author, top_citation, top_cit_per_year]
self.assertEqual(top_results, [' Bishop', 49230, 3077])
self.assertEqual(top_results, [' Bishop', 49230, 2896])

def test_cit_per_year_sorted(self):
df=self.df_top_sorted_cit_per_year
top_citations=list(df.Citations.values[:5])
top_cit_per_year = list(df['cit/year'].values[:5])
top_results = [top_citations, top_cit_per_year]
self.assertEqual(top_results, [[49230, 8603, 2853, 3166, 2416],
[3077, 860, 713, 396, 345]])
[2896, 782, 571, 352, 302]])

def test_csv_exists(self):
os.system("python sortgs.py --debug --kw 'machine learning' --nresults 10")
Expand Down