def test_from_soup(self, get_request, page_instance):
post_html = get_request.text
post_soup = BeautifulSoup(post_html, features='lxml')
post_obj = Post(post_soup)
post_obj.scrape()
assert post_obj.likes == page_instance.likes
def test_from_html(self, get_request, page_instance):
post_html = get_request.text
post_obj = Post(post_html)
post_obj.scrape()
assert post_obj.likes == page_instance.likes
def page_instance(self, url, headers):
random_google_post = Post(url)
random_google_post.scrape(headers=headers)
return random_google_post
import parser_libraries
from selenium import webdriver
from selenium.webdriver import Chrome
from instascrape import Profile, scrape_posts, Post, Hashtag
import time
headers = {"user-agent": "Chrome/87.0.4389.23", "cookie": "sessionid= "}
f = open('input_data.txt', 'r')
posts_codes = []
for line in f:
line = line.split(':')[1]
line = line.split('-')
if (len(line) == 4):
line = line[0].strip(' ')
else:
line = line[0].strip(' ') + '-' + line[1].strip(' ')
posts_codes.append(line)
print(posts_codes)
nafnaf = Profile('nafnafcol')
nafnaf.scrape(headers=headers)
for i in range(len(posts_codes)):
nafnaf_post = Post(posts_codes[i])
nafnaf_post.scrape()
print('----------------------')
print(nafnaf_post.to_dict()['caption'])
time.sleep(10)
def page_instance(self, url):
random_google_post = Post(url)
random_google_post.scrape()
return random_google_post