-
-
Save fnneves/14fd2e05a1e39e67bae5a5ccf50c9975 to your computer and use it in GitHub Desktop.
| hashtag_list = ['travelblog', 'travelblogger', 'traveler'] | |
| # prev_user_list = [] - if it's the first time you run it, use this line and comment the two below | |
| prev_user_list = pd.read_csv('20181203-224633_users_followed_list.csv', delimiter=',').iloc[:,1:2] # useful to build a user log | |
| prev_user_list = list(prev_user_list['0']) | |
| new_followed = [] | |
| tag = -1 | |
| followed = 0 | |
| likes = 0 | |
| comments = 0 | |
| for hashtag in hashtag_list: | |
| tag += 1 | |
| webdriver.get('https://www.instagram.com/explore/tags/'+ hashtag_list[tag] + '/') | |
| sleep(5) | |
| first_thumbnail = webdriver.find_element_by_xpath('//*[@id="react-root"]/section/main/article/div[1]/div/div/div[1]/div[1]/a/div') | |
| first_thumbnail.click() | |
| sleep(randint(1,2)) | |
| try: | |
| for x in range(1,200): | |
| username = webdriver.find_element_by_xpath('/html/body/div[3]/div/div[2]/div/article/header/div[2]/div[1]/div[1]/h2/a').text | |
| if username not in prev_user_list: | |
| # If we already follow, do not unfollow | |
| if webdriver.find_element_by_xpath('/html/body/div[3]/div/div[2]/div/article/header/div[2]/div[1]/div[2]/button').text == 'Follow': | |
| webdriver.find_element_by_xpath('/html/body/div[3]/div/div[2]/div/article/header/div[2]/div[1]/div[2]/button').click() | |
| new_followed.append(username) | |
| followed += 1 | |
| # Liking the picture | |
| button_like = webdriver.find_element_by_xpath('/html/body/div[3]/div/div[2]/div/article/div[2]/section[1]/span[1]/button/span') | |
| button_like.click() | |
| likes += 1 | |
| sleep(randint(18,25)) | |
| # Comments and tracker | |
| comm_prob = randint(1,10) | |
| print('{}_{}: {}'.format(hashtag, x,comm_prob)) | |
| if comm_prob > 7: | |
| comments += 1 | |
| webdriver.find_element_by_xpath('/html/body/div[3]/div/div[2]/div/article/div[2]/section[1]/span[2]/button/span').click() | |
| comment_box = webdriver.find_element_by_xpath('/html/body/div[3]/div/div[2]/div/article/div[2]/section[3]/div/form/textarea') | |
| if (comm_prob < 7): | |
| comment_box.send_keys('Really cool!') | |
| sleep(1) | |
| elif (comm_prob > 6) and (comm_prob < 9): | |
| comment_box.send_keys('Nice work :)') | |
| sleep(1) | |
| elif comm_prob == 9: | |
| comment_box.send_keys('Nice gallery!!') | |
| sleep(1) | |
| elif comm_prob == 10: | |
| comment_box.send_keys('So cool! :)') | |
| sleep(1) | |
| # Enter to post comment | |
| comment_box.send_keys(Keys.ENTER) | |
| sleep(randint(22,28)) | |
| # Next picture | |
| webdriver.find_element_by_link_text('Next').click() | |
| sleep(randint(25,29)) | |
| else: | |
| webdriver.find_element_by_link_text('Next').click() | |
| sleep(randint(20,26)) | |
| # some hashtag stops refreshing photos (it may happen sometimes), it continues to the next | |
| except: | |
| continue | |
| for n in range(0,len(new_followed)): | |
| prev_user_list.append(new_followed[n]) | |
| updated_user_df = pd.DataFrame(prev_user_list) | |
| updated_user_df.to_csv('{}_users_followed_list.csv'.format(strftime("%Y%m%d-%H%M%S"))) | |
| print('Liked {} photos.'.format(likes)) | |
| print('Commented {} photos.'.format(comments)) | |
| print('Followed {} new people.'.format(followed)) |
Do you have pandas installed?
No, I haven't installed pandas, since it was not mentioned on medium article
AND the xpath links have changed as well.
The following xpaths are working for me.
... code block below...
1. username xpaths
username = webdriver.find_element_by_xpath('/html/body/div[4]/div[2]/div/article/header/div[2]/div[1]/div[1]/a').text
if username not in prev_user_list:
if webdriver.find_element_by_xpath('/html/body/div[4]/div[2]/div/article/header/div[2]/div[1]/div[2]/button').text == 'Follow':
webdriver.find_element_by_xpath('/html/body/div[4]/div[2]/div/article/header/div[2]/div[1]/div[2]/button').click()
2. Likes xpaths
# Liking the picture
button_like = webdriver.find_element_by_xpath('/html/body/div[4]/div[2]/div/article/div[2]/section[1]/span[1]/button')
3. comments xpaths webdriver.find_element_by_xpath('/html/body/div[4]/div[2]/div/article/header/div[2]/div[1]/div[2]/button/html/body/div[4]/div[2]/div/article/div[2]/section[1]/span[2]/button').click()
comment_box = webdriver.find_element_by_xpath('/html/body/div[4]/div[2]/div/article/div[2]/section[3]/div/form/textarea')
I have tried by changing the paths, it run successfully able to logged in with username and password but when it opens a hastag then opens its first post then it do not comment on the post and also don't do like it, simply move forwards on another hashtag, Also I got blocked by Instagram by running this bot, though it was not my official account and I got unblocked after 5 hrs.It is working for you?
Without seeing your code, the best I can assume is that like button and comment box paths aren’t found and the program enters the loop again after the sleep time i.e. check if your paths are correct.
For me the only consistent bug was pandas not always appending the csv file. I blame the webdriver.
Question, what's the point of
3. comments xpaths webdriver.find_element_by_xpath('/html/body/div[4]/div[2]/div/article/header/div[2]/div[1]/div[2]/button/html/body/div[4]/div[2]/div/article/div[2]/section[1]/span[2]/button').click()?
Also this xpath doesn't work for me. like we're clicking on the comments box, but not the text area?
@murrman95
Did you omit this line? The variable comment_box is necessary for the following if-else logic to work. You click on the comment button to get the text field but don’t assign the text box’s xpath to the comment_box variable.
comment_box = webdriver.find_element_by_xpath('/html/body/div[4]/div[2]/div/article/div[2]/section[3]/div/form/textarea')
Agreed. The script doesn't handle pandas well. Anyone without a intro to pandas is at a disadvantage. Tho, there is little tweaking to be done for it to work.
hi great medium article
i got error
prev_user_list = pd.read_csv('20181203-224633_users_followed_list.csv', delimiter=',').iloc[:,1:2] # useful to build a user log
NameError: name 'pd' is not definedi have installed pandas and running on python 3.8.2
Thanks! Are you sure you imported pandas as pd initially? The error is pretty clear, it is saying it does not know what pd is...
Let me know!
Imo, every time a new csv should be created with data from old csv fetched and appended to the new file. Alternatively, refine logic so csv output issues are managed.
Agreed. The script doesn't handle pandas well. Anyone without a intro to pandas is at a disadvantage. Tho, there is little tweaking to be done for it to work.
Hi! Thanks for helping out other people with the pandas issue!
Regarding the xpaths, there's no way around it... Instagram changes the structure of the page and it can brake the code. I found a nice tool to get the css path really easy. Look for a chrome extension called SelectorGadjet.
I don't usually update these files, but I'll find some time to optimize that csv part. Thanks!
hi great medium article
i got error
prev_user_list = pd.read_csv('20181203-224633_users_followed_list.csv', delimiter=',').iloc[:,1:2] # useful to build a user log
NameError: name 'pd' is not defined
i have installed pandas and running on python 3.8.2Thanks! Are you sure you imported pandas as pd initially? The error is pretty clear, it is saying it does not know what pd is...
Let me know!
I haven't even tuched the code i just updated the button dom selector and gived some username and password.
so i have
import pandas as pd
in line 5
okey i tried to test it out so
import pandas as pd
pd.test()
It works.
Now when i re-run your instabot2.py i got
Traceback (most recent call last):
File "instabot2.py", line 4, in
prev_user_list = pd.read_csv('20181203-224633_users_followed_list.csv', delimiter=',').iloc[:,1:2] # useful to build a user log
NameError: name 'pd' is not defined
Do you have pandas installed?
No, I haven't installed pandas, since it was not mentioned on medium article
AND the xpath links have changed as well.
The following xpaths are working for me.
... code block below...1. username xpaths username = webdriver.find_element_by_xpath('/html/body/div[4]/div[2]/div/article/header/div[2]/div[1]/div[1]/a').text if username not in prev_user_list: if webdriver.find_element_by_xpath('/html/body/div[4]/div[2]/div/article/header/div[2]/div[1]/div[2]/button').text == 'Follow': webdriver.find_element_by_xpath('/html/body/div[4]/div[2]/div/article/header/div[2]/div[1]/div[2]/button').click() 2. Likes xpaths # Liking the picture button_like = webdriver.find_element_by_xpath('/html/body/div[4]/div[2]/div/article/div[2]/section[1]/span[1]/button') 3. comments xpaths webdriver.find_element_by_xpath('/html/body/div[4]/div[2]/div/article/header/div[2]/div[1]/div[2]/button/html/body/div[4]/div[2]/div/article/div[2]/section[1]/span[2]/button').click()comment_box = webdriver.find_element_by_xpath('/html/body/div[4]/div[2]/div/article/div[2]/section[3]/div/form/textarea')
hey i did this as well and it doesn't work. no errors in the terminal. just not liking, following, or commenting. i checked and rechecked the xpaths... any help?
Followed your medium post (thanks for that btw!) and made some changes on my own to make it work as of November 22.
Instagram seems to have changed slightly and I feel the csv checking whether the username is followed already is unnecessary now as when we follow the user already the follow button is not present.
Also the next button threw some errors as it kept on switching back and forth between picture 1 and 2 since the next button on the second page is not the same as on the first. Instead the bot just clicks the arrow right key to advance.
The log info while the bot progresses now gives a hint whether it left a comment and the csv saves a new file instead of appending the old to not have such a long document.
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
from selenium.webdriver.common.by import By
from time import sleep, strftime
from random import randint
import pandas as pd
import sys
import glob
browser = webdriver.Firefox()
browser.get('https://www.instagram.com/accounts/login/?source=auth_switcher')
sleep(5)
insta_cookies = browser.find_element(By.XPATH, '/html/body/div[4]/div/div/button[1]')
insta_cookies.click()
sleep(4)
username = browser.find_element(By.XPATH,
'/html/body/div[1]/section/main/div/div/div[1]/div[2]/form/div/div[1]/div/label/input')
username.send_keys('USERNAME')
sleep(0.5)
password = browser.find_element(By.XPATH,
'/html/body/div[1]/section/main/div/div/div[1]/div[2]/form/div/div[2]/div/label/input')
password.send_keys('PASSWORD')
sleep(2)
login_button = browser.find_element(By.XPATH,
'/html/body/div[1]/section/main/div/div/div[1]/div[2]/form/div/div[3]/button')
login_button.click()
sleep(8)
info_button = browser.find_element(By.XPATH,
'/html/body/div[1]/div/div/div/div[1]/div/div/div/div[1]/section/main/div/div/div/div/button')
info_button.click()
sleep(4)
alert_button = browser.find_element(By.XPATH,
'/html/body/div[1]/div/div/div/div[2]/div/div/div[1]/div/div[2]/div/div/div/div/div[2]/div/div/div[3]/button[2]')
alert_button.click()
hashtag_list = ['digitalart', 'nftart']
timecode = strftime("%d/%m/%Y_%Hh%Mm%Ss")
path_name = r'C:\Users\USER\PycharmProjects\insta_bot\*.csv'
csv_files = glob.glob(path_name)
last_file = csv_files[-1]
list_count = int(last_file[-6:-4])
user_list = []
new_followed = []
tag = -1
followed = 0
likes = 0
comments = 0
def next_arrow():
browser.find_element(By.XPATH, '/html').send_keys(Keys.ARROW_RIGHT)
for hashtag in hashtag_list:
tag += 1
browser.get('https://www.instagram.com/explore/tags/' + hashtag_list[tag] + '/')
sleep(20)
first_image = browser.find_element(By.XPATH,
'/html/body/div[1]/div/div/div/div[1]/div/div/div/div[1]/section/main/article/div/div/div/div[1]/div[1]/a/div/div[2]')
first_image.click()
sleep(randint(2, 4))
try:
for a in range(1, 100):
username = browser.find_element(By.XPATH,
'/html/body/div[1]/div/div/div/div[2]/div/div/div[1]/div/div[3]/div/div/div/div/div[2]/div/article/div/div[2]/div/div/div[1]/div/header/div[2]/div[1]/div[1]/div/div/div/span/a').text
try:
follow_button = browser.find_element(By.XPATH,
'/html/body/div[1]/div/div/div/div[2]/div/div/div[1]/div/div[3]/div/div/div/div/div[2]/div/article/div/div[2]/div/div/div[1]/div/header/div[2]/div[1]/div[2]/button')
follow_button.click()
new_followed.append(username)
followed += 1
like_button = browser.find_element(By.XPATH,
'/html/body/div[1]/div/div/div/div[2]/div/div/div[1]/div/div[3]/div/div/div/div/div[2]/div/article/div/div[2]/div/div/div[2]/section[1]/span[1]/button')
like_button.click()
likes += 1
sleep(randint(10, 20))
comm_prob = randint(1, 10)
if comm_prob >= 5:
comment_check = True
comment_button = browser.find_element(By.XPATH,
'/html/body/div[1]/div/div/div/div[2]/div/div/div[1]/div/div[3]/div/div/div/div/div[2]/div/article/div/div[2]/div/div/div[2]/section[1]/span[2]/button')
comment_button.click()
comment_box = browser.find_element(By.XPATH,
'/html/body/div[1]/div/div/div/div[2]/div/div/div[1]/div/div[3]/div/div/div/div/div[2]/div/article/div/div[2]/div/div/div[2]/section[3]/div/form/textarea')
if comm_prob == 5:
comment_box.send_keys("Awesome!")
sleep(1)
if comm_prob == 6:
comment_box.send_keys("Nice!")
sleep(1)
elif comm_prob == 7:
comment_box.send_keys("Cool!")
sleep(1)
elif comm_prob == 8:
comment_box.send_keys("Great!")
sleep(1)
elif comm_prob == 9:
comment_box.send_keys("Super!")
sleep(1)
elif comm_prob == 10:
comment_box.send_keys("Fantastic!")
sleep(1)
comment_box.send_keys(Keys.ENTER)
comments += 1
sleep(randint(5, 10))
else:
comment_check = False
if comment_check:
comment_proof = '| commented'
else:
comment_proof = ''
print(f'{a} | #{hashtag} | user: {username} | {strftime("%Hh%Mm%Ss")} {comment_proof}')
next_arrow()
sleep(randint(5, 15))
except Exception:
next_arrow()
sleep(randint(10, 15))
continue
except Exception as e1:
print(f"""> activated exception 2 in line: {sys.exc_info()[-1].tb_lineno} | {e1}""")
next_arrow()
sleep(randint(5, 10))
continue
user_list.extend(new_followed)
list_count += 1
users_updated = pd.DataFrame(user_list)
users_updated.to_csv(f'users-followed-list_0{list_count}.csv')
print(f"""
Liked {likes} posts.
Commented on {comments} posts.
Followed {followed} new profiles.
""")
No, I haven't installed pandas, since it was not mentioned on medium article