获取 Instagram 的点赞者列表 post - Python & Selenium

Question

我正在训练网络抓取。为此，我向自己发起了挑战，要获得所有在 Instagram 上点赞 post 的人的名单。我的问题是我一直坚持只获得喜欢者的前 11 个用户名。我找不到在获得喜欢的同时自动执行滚动过程的正确方法。

这是我在 Jupyter Notebook 中的过程（它还不能作为脚本运行）：

from selenium import webdriver
import pandas as pd

driver = webdriver.Chrome()

driver.get('https://www.instagram.com/p/BuE82VfHRa6/')

userid_element = driver.find_elements_by_xpath('//*[@id="react-root"]/section/main/div/div/article/div[2]/section[2]/div/div/a')[0].click()

elems = driver.find_elements_by_xpath("//*[@id]/div/a")

users = []

for elem in elems:
    users.append(elem.get_attribute('title'))

print(users)

你们有什么想法吗？

非常感谢

Answer 1

请尝试以下代码，如果可行请告诉我。

from selenium import webdriver
driver = webdriver.Chrome()

driver.get('https://www.instagram.com/p/BuE82VfHRa6/')

elems = driver.find_elements_by_xpath("//a[@class='FPmhX notranslate TlrDj']")

users = []

for elem in elems:
    users.append(elem.get_attribute('title'))
    print('Title : ' +elem.get_attribute('title'))

print(users)

输出：-

Title : kyliejenner
Title : saturdayshade28
Title : worldmeetzboy
Title : mrokon
Title : addieisaac
Title : addieisaac
Title : amber_doerksen
Title : amber_doerksen
Title : addieisaac
Title : zayn6117
Title : amber_doerksen
Title : amber_doerksen
Title : worldmeetzboy
Title : worldmeetzboy
Title : razvanpopic1301
Title : johanna.trmn
Title : johanna.trmn
Title : johanna.trmn
Title : americ.av
Title : gabriellcostta1.0
Title : gabriellcostta1.0
Title : gabriellcostta1.0
Title : worldmeetzboy
Title : enactusepi
Title : enactusepi
[u'kyliejenner', u'saturdayshade28', u'worldmeetzboy', u'mrokon', u'addieisaac', u'addieisaac', u'amber_doerksen', u'amber_doerksen', u'addieisaac', u'zayn6117', u'amber_doerksen', u'amber_doerksen', u'worldmeetzboy', u'worldmeetzboy', u'razvanpopic1301', u'johanna.trmn', u'johanna.trmn', u'johanna.trmn', u'americ.av', u'gabriellcostta1.0', u'gabriellcostta1.0', u'gabriellcostta1.0', u'worldmeetzboy', u'enactusepi', u'enactusepi']

Answer 2

我猜 instagram 网站使用最多 17 个喜欢的用户元素。
所以，这是一个循环

从网络获取元素列表
保存到我的列表
向下滚动获取新元素
检查，这是最后一个滚动元素吗？

driver.get('https://www.instagram.com/p/BuE82VfHRa6/')

userid_element = driver.find_elements_by_xpath('//*[@id="react-root"]/section/main/div/div/article/div[2]/section[2]/div/div/a')[0].click()
time.sleep(2)

# here, you can see user list you want.
# you have to scroll down to download more data from instagram server.
# loop until last element with users table view height value.

users = []

height = driver.find_element_by_xpath("/html/body/div[3]/div/div[2]/div/div").value_of_css_property("padding-top")
match = False
while match==False:
    lastHeight = height

    # step 1
    elements = driver.find_elements_by_xpath("//*[@id]/div/a")

    # step 2
    for element in elements:
        if element.get_attribute('title') not in users:
            users.append(element.get_attribute('title'))

    # step 3
    driver.execute_script("return arguments[0].scrollIntoView();", elements[-1])
    time.sleep(1)

    # step 4
    height = driver.find_element_by_xpath("/html/body/div[3]/div/div[2]/div/div").value_of_css_property("padding-top")
    if lastHeight==height:
        match = True

print(users)
print(len(users))
driver.quit()

我测试了将近 100 个赞 post，并且有效。

Answer 3

我无法让代码像 post 在预测的答案中编辑的那样工作。因此，我进行了下面的改编，现在每个 post.

获得了 ~500 个赞

def get_post_likers(shortcode):
    chrome = ch.initialize()
    chrome.get('https://www.instagram.com/p/' + shortcode + '/')
    chrome.execute_script("window.scrollTo(0, 1080)") 
    url = "/p/" + shortcode + "/liked_by/"
    time.sleep(2)
    like_link = chrome.find_element_by_xpath('//a[@href="'+url+'"]')
    like_link.click()
    time.sleep(2)
    users = []
    pb = chrome.find_element_by_xpath("//div[@role = 'dialog']/div[2]/div[1]/div[1]").value_of_css_property("padding-bottom")
    match = False
    while match==False:
        lastHeight = pb

        # step 1
        elements = chrome.find_elements_by_xpath("//*[@id]/div/a")
        # step 2
        for element in elements:
            if element.get_attribute('title') not in users:
                users.append(element.get_attribute('title'))
        # step 3
        chrome.execute_script("return arguments[0].scrollIntoView();", elements[-1])
        time.sleep(1)
        # step 4
        pb = chrome.find_element_by_xpath("//div[@role = 'dialog']/div[2]/div[1]/div[1]").value_of_css_property("padding-bottom")
        if lastHeight==pb or len(users) >= 1500:
            match = True
    return users

Answer 4

这对我有用：

driver.get('https://www.instagram.com/p/BuE82VfHRa6/')

time.sleep(2)

userid_element = driver.find_element_by_xpath('//*[@id="react-root"]/section/main/div/div[1]/article/div[3]/section[2]/div/div[2]/button').click()
time.sleep(2)



elems = driver.find_elements_by_xpath("//a[@class='FPmhX notranslate TlrDj']")

users = []


for i in range(10):
    i += 1
    if(i%10) == 9 :
        driver.find_element_by_xpath('/html/body/div[4]/div/div/div[2]/div').click()
        actionChain.key_down(Keys.SPACE).key_up(Keys.SPACE).perform()

    print('/html/body/div[4]/div/div/div[2]/div/div/div['+str(i)+']/div[2]/div[1]/div/a')
    Title = driver.find_element_by_xpath('/html/body/div[4]/div/div/div[2]/div/div/div['+str(i)+']/div[2]/div[1]/div/a').get_attribute('title')
    users.append(Title)
    print('Title : ' + Title)

print(users)

Answer 5

我尝试了以上所有解决方案，但其中 none 有效。我认为它们已经过时了。

相反，我写了自己的。它在 2020 年完美运行。

此代码转到“用户名”地址并在配置文件中获取最新的 post 并获得喜欢的用户。

def getPosts():
    hrefs_in_view = driver.find_elements_by_tag_name('a')
    # finding relevant hrefs
    hrefs_in_view = [elem.get_attribute('href') for elem in hrefs_in_view
         if '.com/p/' in elem.get_attribute('href')]
    
    return hrefs_in_view;





def getLikers(username,limit,post=1):
    driver.get('https://www.instagram.com/' + username)
    time.sleep(1)
    users=[]

    #Get Latest Post
    driver.get(getPosts()[post])
    
    time.sleep(2)
    #Open Dialog
    followersLinkX = driver.find_element_by_xpath('//button[@class="sqdOP yWX7d     _8A5w5    "]')
    followersLinkX.click()
    time.sleep(1)
    #Get Dialog
    xxx = driver.find_element_by_xpath('//div[@role="dialog"]/div[1]/div[2]/div[1]/div[1]')
    #Focus on and Scroll
    xxx.click()
    # step 3
    actionChain = webdriver.ActionChains(driver)

  

    count = 0
    
    while(count < limit):
        for i in range(1,1000):
            try:
                users.append("https://www.instagram.com/" + driver.find_element_by_xpath('//div[@role="dialog"]/div[1]/div[2]/div[1]/div[1]/div['+ str(i) +']/div[2]/div[1]/div[1]').text) 
                count+=1
            except:
                break
        actionChain.key_down(Keys.SPACE).key_up(Keys.SPACE).perform()
        time.sleep(0.5)  

    return users

运行likers = getLikers("deirvlon",100,1)

获取 Instagram 的点赞者列表 post - Python & Selenium

Getting list of likers for an instagram post - Python & Selenium

python

selenium

web-crawler

instagram