Instagram - Scraper

#Define variaveis conta_ig = 'xxxx' mes = 3 ano = 2021 path_posts = './dados_scraper/posts_' + conta_ig + '.csv' path_resultado = './dados_scraper//comments_' + conta_ig + '/' + 'comments_' + conta_ig + '_' + str(ano) + '_' + str(mes) + '.csv' print('CONFIGURAÇÕES:') print('Conta IG: ' + conta_ig) print('Mês:' + str(mes)) print('Ano:' + str(ano)) print('Lista de posts em: ' + path_posts) print('Resultados serão salvos em: ' + path_resultado)

# Carrega bibliotecas from igramscraper.exception.instagram_auth_exception import InstagramAuthException from igramscraper.exception.instagram_exception import InstagramException from igramscraper.exception.instagram_not_found_exception import InstagramNotFoundException from igramscraper.instagram import Instagram import pandas as pd import time from random import seed from random import randint from proxies_credentials import proxyA, proxyB, proxyC, proxyD, proxyE, proxyF, proxyG, proxyH, proxyI, proxyJ, proxyK, proxyL

# Define proxy a ser usado #C proxies = proxyC() #inicializa Instagram e define o proxy instagram = Instagram() instagram.set_proxies(proxies) instagram.set_user_agent('Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:77.0) Gecko/20100101 Firefox/77.0')

# Define conta do Instagram a ser usada instagram.with_credentials('xxxx','xxxx','./dados_scraper') # Estabelece login na conta print('preparando para instagram login') instagram.login() print('login feito')

## Inicia processamento # Get media comments by shortcode posts = pd.read_csv(path_posts) posts['dt_post'] = pd.to_datetime(posts['created_time'], unit='s') posts['year'] = posts['dt_post'].dt.year posts['month'] = posts['dt_post'].dt.month posts = posts[(posts.year == ano) & (posts.month == mes)] posts = posts[['short_code']].drop_duplicates() print('Qtd de Posts: ' + str(len(posts.index))) lista_posts = posts.short_code.tolist() lista_comments= [] i = 1 p = 1 seed(22) for post in lista_posts: random_seg = randint(0, 40) + 40 if i == 5: random_seg += 600 i = 0 i += 1 print('pausa: ' + str(random_seg) +' seg') time.sleep(random_seg) print('Processando post: ' + str(p)) comments = instagram.get_media_comments_by_code(post,1000) print('...Qtd de Comentarios: ' + str(len(comments['comments']))) p += 1 for comment in comments['comments']: lista_comments.append({ "id_post": post, "id_comment": comment.identifier, "created_at": comment.created_at, "id_user": comment.owner.identifier, "username": comment.owner.username, "text": comment.text }) df_comments = pd.DataFrame.from_dict(lista_comments) df_comments.to_csv(path_resultado) print('FINALIZADO: ' + str(len(df_comments.index))+ ' commentarios processados em ' + str(len(posts.index)) + ' posts.') print('Salvos em: ' + path_resultado) df_comments