def export_csv(aid_data): csw = CommonCsvWriter(filename='./output/stat_HARDCORE-1005') csw.write_header(['date','aid','guid','guid_name','chechin No','view','click','share']) csv_body = [] keylist = aid_data.keys() keylist.sort() for key in keylist: aid = key datas = aid_data.get(key) for data in datas: d_key_list = data.keys() d_key_list.sort() date = data['date_str'] for d_key in d_key_list: if d_key == 'date_str': continue guid = d_key checkin_c = get_post_count_by_guid(guid) loc_name = get_location(guid) num = data.get(d_key) #print aid,guid,num csv_body.append([date,aid,guid,loc_name,checkin_c,num[0],num[1],num[2]]) csw.write_body(csv_body) csw.end_write()
def export_csv(guids): csw = CommonCsvWriter(filename='./output/stat_HM') csw.write_header(['date','aid','guid','guid_name','chechin No','view','click','share']) csv_body = [] for guid in guids: posts = get_posts_by_guid(guid, detail=True) for post in posts: row = [post['u'],post['l'],post['c'],post['b'].replace('\r','').replace('\n','')] has_photo = 'Yes' if db_slave.photo.find_one({'p':post['_id']}) else 'No' row.append(has_photo) url = 'http://jiepang.com/user/story?pid=%s' % str(post['_id']) row.append(url) csv_body.append(row) csw.write_body(csv_body) csw.end_write()
def get_target_guids(): # guids = [] return stat_util.get_vertical_list_from_csv(INPUT_FILE_PATH, 2) def stat_user_lists(target_guids): start_date = datetime.datetime.utcnow() - datetime.timedelta(days=60) stat_timestamp = stat_util.convert_datetime_to_timestamp(start_date) user_ids = set() for guid in target_guids: int_guid = guid_to_int(guid) for r in crab.location_post[int_guid].find(R.created_on > stat_timestamp).group(R.user_id): user_ids.add(r["user_id"]) return user_ids if __name__ == "__main__": target_guids = get_target_guids() # print target_guids user_ids = stat_user_lists(target_guids) csw = CommonCsvWriter("subway_userlist") csw.write_header([u"user_id"]) csv_body = [] for uid in user_ids: csv_body.append([uid]) csw.write_body(csv_body) csw.end_write()