Created
January 18, 2020 11:47
-
-
Save SeolHa314/5826933e191115e83f2e00b9cfaf253a to your computer and use it in GitHub Desktop.
Get Nijisanji liver's twitter username and Youtube channel ids.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import requests | |
import re | |
import json | |
from concurrent.futures import ThreadPoolExecutor, as_completed | |
from bs4 import BeautifulSoup as bs | |
index = 1 | |
endIndex = 0 | |
def get_you_twt(url, session): | |
global index | |
global endIndex | |
r = session.get(url) | |
r.raise_for_status() | |
if r.ok: | |
liverpage = bs(r.content, "lxml") | |
name_both = liverpage.select("body > div > div:nth-of-type(2) > div > div > section:nth-of-type(1) > div > div > div:nth-of-type(2) > div > div > div:nth-of-type(2) > div > h2")[0].get_text() | |
name_english = name_both[name_both.find("/") + 1:] | |
for a in liverpage.find_all("a",href=True): | |
if "twitter.com" in a["href"]: | |
twitter_id = a["href"][20:] | |
elif "youtube.com" in a["href"]: | |
youtube_id = a["href"][32:56] | |
print(str(index / (endIndex + 1) * 100) + "%% ended.") | |
index += 1 | |
return (name_english, twitter_id, youtube_id) | |
r = requests.get("https://nijisanji.ichikara.co.jp/member/") | |
r.raise_for_status() | |
soup = bs(r.content, "lxml") | |
url_lists = [] | |
for i in soup.select("#liver_list > div"): | |
url_lists.append(i.div.div.a["href"]) | |
endIndex = url_lists.__len__() | |
session = requests.Session() | |
dict_livers = dict() | |
with ThreadPoolExecutor(max_workers=10) as executor: | |
future_livers = [executor.submit(get_you_twt, url=url_lists[i], session=session) for i in range(endIndex)] | |
for future in as_completed(future_livers): | |
try: | |
data = future.result() | |
except Exception as exc: | |
print(exc) | |
else: | |
dict_livers[data[0]] = { | |
"twitter": data[1], | |
"youtube": data[2] | |
} | |
with open("liver1.json", "w") as f: | |
json.dump(dict_livers, f, indent=4) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment