def test():
# database.del_all("movie")
database.del_all("comment")
# database.insert_movie(spider.getMoviesInfor(10))
database.insert_comment(spider.getMovieShortComments(32659890, 20, proxy=1), 32659890)
# # No more than 10 pages. getMovieShortComments()方法不要爬10页以上，因为豆瓣限制了短评页数。
# print(database.get_movies())
# print(database.get_comments(26885074))
pass
def new_comment():
data = request.get_json()
print 'Received comment "{0}" for {1} from {2}'.format(
data['comment'], data['url'], data['user_id'])
comment = Comment(data['user_id'],
data['url'],
data['comment'])
database.insert_comment(g.db.cursor(), comment)
g.db.commit()
# TODO: Fix me. For now, respond with nothing and 204 No Content
return ('', 204)
def insert_comment():
meeting_id = request.form["id"]
comment = request.form["comment"]
chat_id = database.get_chat_id(meeting_id)
database.insert_comment(chat_id, comment)
return "your comment was inserted"
# Insert the post
database.insert_post(connection=connection,
post_id=post_id,
username=username,
sub_name=sub_name,
title=title,
score=score,
nsfw=nsfw)
# Get top 100 comments of that post
for comment in comments[:100]:
try:
username = comment.author.name
except AttributeError:
username = "******"
comment_id = comment.id
# Insert comment
database.insert_comment(connection=connection,
comment_id=comment_id,
post_id=post_id,
username=username)
# Commit the post and comments
connection.commit()
# Close the connection at the end
connection.close()
import database
con = database.set_up_db("check.db");
cur= con.cursor()
database.create_table(cur)
database.insert_comment(cur, "Isha", "Trying hard")
print(database.get_comments(cur))
# database.drop_all_tables(cur)
con.commit()
con.close()
area = matchObj.group(1)
sex = matchObj2.group(1)
except Exception as e:
print("re Error.")
print(e)
commentList.append(
{'id': commentbody['id'],
'text': commentbody['text'],
'time': commentbody['created_at'],
'name': commentbody['user']["screen_name"],
"area": area,
"sex": sex})
last_max_id = jsondatum['data']['max_id']
last_max_id_type = jsondatum['data']['max_id_type']
page += 1
print(page)
time.sleep(random.randint(1, 4))
return commentList
if __name__ == '__main__':
login("18214888360", "6366565")
commentlist = getComments(2000)
print("爬到" + str(len(commentlist)) + "条")
util_csv.save_csv(commentlist)
database.insert_comment(commentlist)
# coding=utf-8
# Code by SmallSquare, 2020/5.
# An example that show how to prepare data before wordCloudAnalysis.
# 展示如何在数据分析之前获得数据。
import spider.spider_main as spider
import database
# Use spider like following.
# 这样用爬虫爬数据。
database.del_all("movie")
database.del_all("comment")
database.insert_movie(spider.getMoviesInfor(10))
database.insert_comment(spider.getMovieShortComments(26885074, 2), 26885074)
# Get data from database.
# 这样获取数据库里的数据。
print(database.get_movies())
print(database.get_comments(26885074))