optimise scraping and requesting web page - python-3.x

Question

How should I optimise my time in making requests
link=['http://youtube.com/watch?v=JfLt7ia_mLg',
'http://youtube.com/watch?v=RiYRxPWQnbE'
'http://youtube.com/watch?v=tC7pBOPgqic'
'http://youtube.com/watch?v=3EXl9xl8yOk'
'http://youtube.com/watch?v=3vb1yIBXjlM'
'http://youtube.com/watch?v=8UBY0N9fWtk'
'http://youtube.com/watch?v=uRPf9uDplD8'
'http://youtube.com/watch?v=Coattwt5iyg'
'http://youtube.com/watch?v=WaprDDYFpjE'
'http://youtube.com/watch?v=Pm5B-iRlZfI'
'http://youtube.com/watch?v=op3hW7tSYCE'
'http://youtube.com/watch?v=ogYN9bbU8bs'
'http://youtube.com/watch?v=ObF8Wz4X4Jg'
'http://youtube.com/watch?v=x1el0wiePt4'
'http://youtube.com/watch?v=kkeMYeAIcXg'
'http://youtube.com/watch?v=zUdfNvqmTOY'
'http://youtube.com/watch?v=0ONtIsEaTGE'
'http://youtube.com/watch?v=7QedW6FcHgQ'
'http://youtube.com/watch?v=Sb33c9e1XbY']
I have a list of 15-20 links of youtube search result of first page Now the task is to get the likes,dislikes,view count from each video url and for that what I had done is
def parse(url,i,arr):
req=requests.get(url)
soup = bs4.BeautifulSoup(req.text,"lxml")#, 'html5lib')
try:
likes=int(soup.find("button",attrs={"title": "I like this"}).getText().__str__().replace(",",""))
except:
likes=0
try:
dislikes=int(soup.find("button",attrs={"title": "I dislike this"}).getText().__str__().replace(",",""))
except:
dislikes=0
try:
view=int(soup.find("div",attrs={"class": "watch-view-count"}).getText().__str__().split()[0].replace(",",""))
except:
view=0
arr[i]=(likes,dislikes,view,url)
time.sleep(0.3)
def parse_list(link):
arr=len(link)*[0]
threadarr=len(link)*[0]
import threading
a=time.clock()
for i in range(len(link)):
threadarr[i]=threading.Thread(target=parse,args=(link[i],i,arr))
threadarr[i].start()
for i in range(len(link)):
threadarr[i].join()
print(time.clock()-a)
return arr
arr=parse_list(link)
Now I am getting the populated result array in about 6 seconds.Is there any faster way I can get my array(arr) so that it takes quite less time than 6 secs
my array first 4 elements look like so that you get a rough idea
[(105, 11, 2836, 'http://youtube.com/watch?v=JfLt7ia_mLg'),
(32, 18, 5420, 'http://youtube.com/watch?v=RiYRxPWQnbE'),
(45, 3, 7988, 'http://youtube.com/watch?v=tC7pBOPgqic'),
(106, 38, 4968, 'http://youtube.com/watch?v=3EXl9xl8yOk')]
Thanks in advance :)

Answer 1

I would use multiprocessing Pool object for that particular case.
import requests
import bs4
from multiprocessing import Pool, cpu_count
links = [
'http://youtube.com/watch?v=JfLt7ia_mLg',
'http://youtube.com/watch?v=RiYRxPWQnbE',
'http://youtube.com/watch?v=tC7pBOPgqic',
'http://youtube.com/watch?v=3EXl9xl8yOk'
]
def parse_url(url):
req=requests.get(url)
soup = bs4.BeautifulSoup(req.text,"lxml")#, 'html5lib')
try:
likes=int(soup.find("button", attrs={"title": "I like this"}).getText().__str__().replace(",",""))
except:
likes=0
try:
dislikes=int(soup.find("button", attrs={"title": "I dislike this"}).getText().__str__().replace(",",""))
except:
dislikes=0
try:
view=int(soup.find("div", attrs={"class": "watch-view-count"}).getText().__str__().split()[0].replace(",",""))
except:
view=0
return (likes, dislikes, view, url)
pool = Pool(cpu_count) # number of processes
data = pool.map(parse_url, links) # this is where your results are
This is cleaner as you only have one function to write and you end up with exactly the same results.

Answer 2

This is not a workaround but it can save your script from using "try/except block" which definitely plays a role to somewhat slow the operation down.
for url in links:
response = requests.get(url).text
soup = BeautifulSoup(response,"html.parser")
for item in soup.select("div#watch-header"):
view = item.select("div.watch-view-count")[0].text
likes = item.select("button[title~='like'] span.yt-uix-button-content")[0].text
dislikes = item.select("button[title~='dislike'] span.yt-uix-button-content")[0].text
print(view, likes, dislikes)