我正在尝试编写一个Web抓取python程序，用来登录用户的故事。我认为看看我是否能够正常工作会很有趣，因为4k Stogram只是为了获得更多功能而花钱。
我登录成功，但我不知道从哪里开始。
from bs4 import BeautifulSoup
import json, random, re, requests, urllib.request
import urllib2
USERNAME = '*****'
PASSWD = '****'
account_purging = '****'
BASE_URL = 'https://www.instagram.com/accounts/login/'
LOGIN_URL = BASE_URL + 'ajax/'
headers_list = [
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; FSL 7.0.6.01001)",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; FSL 7.0.7.01001)",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; FSL 7.0.5.01003)",
"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:12.0) Gecko/20100101 Firefox/12.0",
"Mozilla/5.0 (X11; U; Linux x86_64; de; rv:1.9.2.8) Gecko/20100723 Ubuntu/10.04 (lucid) Firefox/3.6.8",
"Mozilla/5.0 (Windows NT 5.1; rv:13.0) Gecko/20100101 Firefox/13.0.1",
"Mozilla/5.0 (Windows NT 6.1; WOW64; rv:11.0) Gecko/20100101 Firefox/11.0",
"Mozilla/5.0 (X11; U; Linux x86_64; de; rv:1.9.2.8) Gecko/20100723 Ubuntu/10.04 (lucid) Firefox/3.6.8",
"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.0; .NET CLR 1.0.3705)",
"Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0)",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; .NET CLR 2.0.50727; .NET CLR 3.0.4506.2152; .NET CLR 3.5.30729)",
"Opera/9.80 (Windows NT 5.1; U; en) Presto/2.10.289 Version/12.01",
"Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; SV1; .NET CLR 2.0.50727)",
"Mozilla/5.0 (Windows NT 5.1; rv:5.0.1) Gecko/20100101 Firefox/5.0.1",
"Mozilla/5.0 (Windows NT 6.1; rv:5.0) Gecko/20100101 Firefox/5.02",
"Mozilla/5.0 (Windows NT 6.0) AppleWebKit/535.1 (KHTML, like Gecko) Chrome/13.0.782.112 Safari/535.1",
"Mozilla/4.0 (compatible; MSIE 6.0; MSIE 5.5; Windows NT 5.0) Opera 7.02 Bork-edition [en]"
]
USER_AGENT = headers_list[random.randrange(0,(len(headers_list)+1))]
session = requests.Session()
session.headers = {'user-agent': USER_AGENT}
session.headers.update({'Referer': BASE_URL})
req = session.get(BASE_URL)
soup = BeautifulSoup(req.content, 'html.parser')
body = soup.find('body')
pattern = re.compile('window._sharedData')
script = body.find("script", text=pattern)
script = script.get_text().replace('window._sharedData = ', '')[:-1]
data = json.loads(script)
csrf = data['config'].get('csrf_token')
login_data = {'username': USERNAME, 'password': PASSWD}
session.headers.update({'X-CSRFToken': csrf})
login = session.post(LOGIN_URL, data=login_data, allow_redirects=True)
story_page = "https://www.instagram.com/stories" + "/" + account_purging
# stories url is:
request_headers_story = {
"Accept:" : "video/webm,video/ogg,video/*;q…q=0.7,audio/*;q=0.6,*/*;q=0.5",
"Accept-Language" : "en-US,en;q=0.5",
"Connection" : "keep-alive",
"DNT" : "1",
"Host" : "scontent-ort2-1.cdninstagram.com",
"Range" : "bytes=0-",
"Referer" : story_page,
"TE" : "Trailers",
"User-Agent" : USER_AGENT
}
soup = session.post(story_page, data=request_headers_story, allow_redirects=True)
print(BeautifulSoup(soup.content, 'html.parser'))
我正在尝试获取mp4和jpg链接并使用它稍后在数组或其他东西中下载。如果有什么可以指向我，我会很感激。
我也试图避免使用api，因为这只会让它变得无聊。
避免使用api的这个问题的更容易的解决方案是使用硒。通过使用硒，您可以更快更有效地登录，并获取您需要的图像和视频。
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
driver = webdriver.Firefox()
#or driver = webdriver.Chrome()
注意：要获取图像，您需要找到图像的ID或名称，并执行以下操作：
driver.find_element_by_id("image_id")
要么
driver.find_element_by_name("image_name")
如果您需要更多信息或说明，请查看https://selenium-python.readthedocs.io/。
如果有帮助，请告诉我！