webscraper/twitter.py at master · urmilshroff/webscraper · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
import bs4
import requests
import operator
from halo import Halo

user_id = input("Enter the username of the Twitter profile:\n")
user_link = "https://twitter.com/" + user_id

spinner = Halo(text="Scraping info...", spinner="dots")
spinner.start()

res = requests.get(user_link)
soup = bs4.BeautifulSoup(res.text, "lxml")

name = soup.select(".ProfileHeaderCard-nameLink.u-textInheritColor.js-nav")

try:
    count = []
    for item in soup.findAll("span", {"class": "ProfileNav-value"}):
        count.append(item.get("data-count"))
except IndexError:
    print("Error: missing or broken info!")

try:
    join = soup.select(".ProfileHeaderCard-joinDateText.js-tooltip.u-dir")
    joined = join[0].get("title")
except IndexError:
    print("Error: missing or broken info!")

spinner.stop()

try:
    print("\nSummary for Twitter user @{} (aka {}):".format(
        user_id, name[0].text))
except IndexError:
    print("Error: missing or broken info!")

try:
    print("\nNumber of Tweets: {}".format(count[0]))
    print("Number of following: {}".format(count[1]))
    print("Number of followers: {}".format(count[2]))
    print("Number of likes: {}".format(count[3]))
    print("Number of lists: {}".format(count[4]))
    print("Number of moments: {}".format(count[5]))
except IndexError:
    print("Error: missing or broken info!")

try:
    print("\nJoined Twitter at: {}".format(joined))
except IndexError:
    print("Error: missing or broken info!")