IBM_post_data_scraper_and_visualization/IBM_linkedin_data_chrome.py at main · Volcano-Dragon/IBM_post_data_scraper_and_visualization · 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
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
#import required libraries
from selenium import webdriver
from selenium.webdriver.common.by import By
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.common.exceptions import TimeoutException
import time
from datetime import datetime as dt
import pyperclip as pc
import regex as re
import csv


#from selenium.webdriver.edge.service import Service as EdgeService
#from webdriver_manager.microsoft import EdgeChromiumDriverManager

from selenium.webdriver.chrome.options import Options
from selenium.webdriver.chrome.service import Service

options = Options()
options.add_argument(r"--user-data-dir=C:\Users\AMD HOME\AppData\Local\Google\Chrome\User Data") #e.g. C:\Users\You\AppData\Local\Google\Chrome\User Data
options.add_argument(r'--profile-directory=Default')
options.add_argument(r'--max_old_space_size=4096')#e.g. Profile 3


#Page request

##edge_options = webdriver.EdgeOptions()
##edge_options.use_chromium = True
##edge_options.add_argument("user-data-dir=C:\\Users\\AMD HOME\\AppData\\Local\\Microsoft\\Edge\\User Data")
##edge_options.add_argument("profile-directory=Default")
##
##driver = webdriver.Edge(service=EdgeService(EdgeChromiumDriverManager().install()),options = edge_options)
service = Service(executable_path=r'C:\Users\AMD HOME\Documents\chromedriver_win32\c\chromedriver.exe')
driver = webdriver.Chrome(service=service, options=options)

driver.get("https://www.linkedin.com/company/ibm/posts/?feedView=all")
time.sleep(1)
driver.find_elements(By.XPATH, """/html/body/div[4]/div[3]/div/div[2]/div/div[2]/main/div[2]/div/div[2]/div[1]/div/button[3]""")[0].click()
typ = driver.find_elements(By.XPATH, """/html/body/div[4]/div[3]/div/div[2]/div/div[2]/main/div[2]/div/div[2]/div[1]/div/button[3]""")[0].text

#time.sleep(5)#Time for loading
##driver.find_elements(By.XPATH, """/html/body/div[4]/div[3]/div/div[2]/div/div[2]/main/div[2]/div/div[2]/div[2]/div/button""")[0].click()
##time.sleep(2)
##driver.find_elements(By.XPATH, """/html/body/div[4]/div[3]/div/div[2]/div/div[2]/main/div[2]/div/div[2]/div[2]/div/div/div/ul/li[2]/div/button""")[0].click()
##time.sleep(2)
#driver.execute_script("window.scrollTo(0, 1800)")
with open("IBM_post_data.csv","x", newline='') as file:
            wr = csv.writer(file)
            wr.writerow(["postID", "tm_stamp", "typ", "fol", "react", "comments", "repost", "edit", "link", "exact_date"])
a = 0
b = 0
with open("text_data.txt","x") as file:
    pass
#driver.close()
for i in range(1,500):
   # driver = webdriver.Chrome(service=service, options=options)
    print(f"{i} post str")
    WebDriverWait(driver, 2000).until(
    EC.presence_of_element_located((By.XPATH, f"""/html/body/div[4]/div[3]/div/div[2]/div/div[2]/main/div[2]/div/div[2]/div[2]/div/div[1]/div[{i}]/div/div/div/div/div""")))
    text = driver.find_elements(By.XPATH, f"""/html/body/div[4]/div[3]/div/div[2]/div/div[2]/main/div[2]/div/div[2]/div[2]/div/div[1]/div[{i}]/div/div/div/div/div""")[0].text
    if 'IBM reposted this' in text:
        print('Repost wala')
        size = driver.find_elements(By.XPATH, f"""/html/body/div[4]/div[3]/div/div[2]/div/div[2]/main/div[2]/div/div[2]/div[2]/div/div[1]/div[{i+1}]""")[0].size
        b += size['height']
        driver.execute_script(f"window.scrollTo({a}, {b})")
        print('a: ',a," b: ",b)
        WebDriverWait(driver, 200).until(
        EC.presence_of_element_located((By.XPATH, f"""/html/body/div[4]/div[3]/div/div[2]/div/div[2]/main/div[2]/div/div[2]/div[2]/div/div[1]/div[{i}]/div/div/div/div/div""")))
        a = b
        with open("text_data.txt","a",encoding="utf-8") as file:
            file.write(f'{i} post str\n'+text+'\n{i} post end\n\n')
        continue
    with open("text_data.txt","a",encoding="utf-8") as file:
        file.write(f'{i} post str\n'+text+'\n{i} post end\n\n')
    #print(text)
    fol = int(re.findall('\d(?:\d|,|)+\d followers*', text)[0].split(' ')[0].replace(',',''))

    all_react = re.findall('\d(?:\d|,|)*\d\s(?:(?:.*?)others*\s)*(?:(?:\d|,|)*\d comments*\s)?(?:(?:\d|,|)*\d reposts*\s)?(?:.*?)\sComment\sRepost\sSend',text)[0].split('\n')
    if len(all_react)>7:
        print(all_react.pop(1))

    react = int(all_react[0].replace(',',''))

    if len(all_react)>5 and 'comment' in all_react[1]:
        comments = int(all_react[1].split(' ')[0].replace(',',''))
    else:
        comments = 0

    if len(all_react)>5 and ('repost' in all_react[2] or 'repost' in all_react[1]):
        pos = 2 if 'comment' in all_react[1] else 1
        repost = int(all_react[pos].split(' ')[0].replace(',',''))
    else:
        repost = 0


    edit = 'yes' if len(re.findall('\d(\?:d|,|)*\d followers\s.*• Edited •', text))>0 else 'no'

    try:

        #/html/body/div[4]/div[3]/div/div[2]/div/div[2]/main/div[2]/div/div[2]/div[2]/div/div[1]/div[1]/div/div/div/div/div/div[3]/div/button
        #/html/body/div[4]/div[3]/div/div[2]/div/div[2]/main/div[2]/div/div[2]/div[3]/div/div[1]/div[{i}]/div/div/div/div/div/div[3]/div/button
        #/html/body/div[4]/div[3]/div/div[2]/div/div[2]/main/div[2]/div/div[2]/div[2]/div/div[1]/div[1]/div/div/div/div/div/div[3]/div/button
        driver.find_elements(By.XPATH, f"""/html/body/div[4]/div[3]/div/div[2]/div/div[2]/main/div[2]/div/div[2]/div[2]/div/div[1]/div[{i}]/div/div/div/div/div/div[3]/div/button""")[0].click()
        WebDriverWait(driver, 200).until(
        EC.presence_of_element_located((By.XPATH, f"""/html/body/div[4]/div[3]/div/div[2]/div/div[2]/main/div[2]/div/div[2]/div[2]/div/div[1]/div[{i}]/div/div/div/div/div/div[3]/div/div/div/ul/li[2]""")))
        driver.find_elements(By.XPATH, f"""/html/body/div[4]/div[3]/div/div[2]/div/div[2]/main/div[2]/div/div[2]/div[2]/div/div[1]/div[{i}]/div/div/div/div/div/div[3]/div/div/div/ul/li[2]""")[0].click()

        ##/html/body/div[4]/div[3]/div/div[2]/div/div[2]/main/div[2]/div/div[2]/div[3]/div/div[1]/div[{i}]/div/div/div/div/div/div[3]/div/div/div/ul/li[2]
        #/html/body/div[4]/div[3]/div/div[2]/div/div[2]/main/div[2]/div/div[2]/div[2]/div/div[1]/div[1]/div/div/div/div/div/div[3]/div/div/div/ul/li[2]
        #driver.execute_script("arguments[0].click();", g)
        time.sleep(1)
        link = pc.paste()
        postID = re.findall('[0-9]{19}', link)
        tm_stamp = (int(postID[0]) >> len(bin(int(postID[0])))-43)//1000
        exact_date = dt.fromtimestamp(tm_stamp).strftime('%d-%m-%Y')
        #exact_date = time.ctime(tm_stamp)
        size = driver.find_elements(By.XPATH, f"""/html/body/div[4]/div[3]/div/div[2]/div/div[2]/main/div[2]/div/div[2]/div[2]/div/div[1]/div[{i+1}]""")[0].size
        #print(size)


        b += size['height']
        driver.execute_script(f"window.scrollTo({a}, {b})")
        print('a: ',a," b: ",b)
        WebDriverWait(driver, 200).until(
        EC.presence_of_element_located((By.XPATH, f"""/html/body/div[4]/div[3]/div/div[2]/div/div[2]/main/div[2]/div/div[2]/div[2]/div/div[1]/div[{i}]/div/div/div/div/div""")))
        a = b

        #print("yus i executed")
        #print('fol: \n',fol,'\nreact: \n',react,'\nedit: \n',edit,'\npostID:\n',postID)
        #ind = text.rfind('•')
        #txt = text[ind:ind+30].casefold().replace('\n',' ')

        #print("Post ID: "+postID[0],"Type: "+typ,"followers: "+fol[0],"Reaction: "+react,"Edited : "+edit,"Link: "+link,sep='\n')
        row = [int(postID[0]), tm_stamp, typ, fol, react, comments, repost, edit, link, exact_date]
        #["postID", "tm_stamp", "typ", "fol", "react", "comments", "repost", "edit", "link", "exact_date"]
        #print(row)

        with open("IBM_post_data.csv","a",newline='') as file:
            wr = csv.writer(file)
            wr.writerow(row)

    except Exception as e:
        print(f"not real post i value = {i}")
        print(traceback.format_exc())
        print(e)


##        driver.execute_script(f"window.scrollTo({a}, {b})")
##        time.sleep(5)
##        a = b
##        b = b+80
##        print("I also")


    print(f"{i}post end")
 #   driver.close()

print("All done")