Chewing_Bever
/
didier
mirror of https://github.com/stijndcl/didier
0
0
Fork 0
Code Issues Projects Releases Wiki Activity

Add comments

pull/30/head
Stijn De Clercq 2021-01-24 13:14:44 +01:00
parent 83f28d9e21
commit 652238ce55
2 changed files with 10 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
cogs/google.py
View File

@ -24,11 +24,9 @@ class Google(commands.Cog):
if results is None: if results is None:
return await ctx.send("Er ging iets fout (Response {})".format(status)) return await ctx.send("Er ging iets fout (Response {})".format(status))
# Filter out all Nones
elements = list(filter(lambda x: x is not None, results)) elements = list(filter(lambda x: x is not None, results))
if len(elements) > 10:
elements = elements[:10]
embed = discord.Embed(colour=discord.Colour.blue()) embed = discord.Embed(colour=discord.Colour.blue())
embed.set_author(name="Google Search") embed.set_author(name="Google Search")
@ -37,6 +35,10 @@ class Google(commands.Cog):
embed.description = "Geen resultaten gevonden." embed.description = "Geen resultaten gevonden."
return await ctx.reply(embed=embed, mention_author=False) return await ctx.reply(embed=embed, mention_author=False)
# Cut excess results out
if len(elements) > 10:
elements = elements[:10]
links = [] links = []
for index, (link, title) in enumerate(elements): for index, (link, title) in enumerate(elements):

5
functions/scraping.py
View File

@ -24,8 +24,12 @@ def google_search(query):
bs = BeautifulSoup(resp.text, "html.parser") bs = BeautifulSoup(resp.text, "html.parser")
def getContent(element): def getContent(element):
"""
Function to find links & titles in the HTML of a <div> element
"""
link = element.find("a", href=True) link = element.find("a", href=True)
title = element.find("h3") title = element.find("h3")
if link is None or title is None: if link is None or title is None:
return None return None
@ -35,6 +39,7 @@ def google_search(query):
return None return None
return link["href"], sp.text return link["href"], sp.text
divs = bs.find_all("div", attrs={"class": "g"}) divs = bs.find_all("div", attrs={"class": "g"})
return list(getContent(d) for d in divs), 200 return list(getContent(d) for d in divs), 200