def _load_hashtag_data(tags: list):
"""Scrape hashtag data for the given hashtags"""
hashtag_objs = []
with tqdm.tqdm(total=len(tags), position=0) as progress:
for tag in tags:
time.sleep(abs(np.random.normal(3, 2)))
hashtag = Hashtag.from_hashtag(tag)
hashtag.static_load()
hashtag_objs.append({
"hashtag": tag,
"posts": hashtag.amount_of_posts,
"datetime": datetime.datetime.now()
})
progress.update(1)
return hashtag_objs
def test_from_hashtag(self, page_instance):
expected_hashtag = "kotlin"
result_profile: Hashtag = Hashtag.from_hashtag(hashtag=expected_hashtag)
assert result_profile.url == page_instance.url
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
sys.path.insert(0, os.path.abspath(".."))
from instascrape import Hashtag
# We will start by running a loop and scraping data at random intervals until the predefined timeframe has elapsed.
# In[2]:
# Metadata
TOTAL_TIME = 60 # Total time
WAIT_TIME = 5 # Mean wait time for random normal distribution
photography = Hashtag.from_hashtag("photography")
instagram = Hashtag.from_hashtag("instagram")
# Create a list of tuples containing data scraped at random
# intervals during the time period
current_time = datetime.datetime.now()
end_time = current_time + datetime.timedelta(seconds=TOTAL_TIME)
photography_data = []
instagram_data = []
while current_time < end_time:
# Wait for normally randomized amount of time
rand_time = abs(np.random.normal(WAIT_TIME, 1.5))
time.sleep(WAIT_TIME)
# Scrape data and append to respective lists
photography.static_load()
def test_from_hashtag(kotlin_hashtag):
result_hashtag: Hashtag = Hashtag.from_hashtag(hashtag=kotlin_hashtag.name)
result_hashtag.static_load()
assert result_hashtag.url == kotlin_hashtag.url
assert result_hashtag.name == kotlin_hashtag.name
def test_from_hashtag(kotlin_hashtag):
result_hashtag: Hashtag = Hashtag.from_hashtag(hashtag=kotlin_hashtag.name)
assert result_hashtag.url == kotlin_hashtag.url