if __name__ == "__main__":
if os.path.exists("topic_frame.csv"):
print("is ok")
read_topic_frame = pd.read_csv("topic_frame.csv", names=["url", "account"])
final_frame = read_topic_frame.sort(["account"], ascending=False).head(10)
print(final_frame)
urls = final_frame['url']
my_hosts = []
for url in urls:
host = "https://testerhome.com/topics/{}".format(url)
my_hosts.append(host)
final_frame['url'] = np.array(my_hosts)
print(final_frame)
final_frame.to_csv(path_or_buf="topic_top.csv", header=True, index=True)
else:
print("file not exist, need to spider")
for page_index in range(max_page):
get_detail(page_index)
final_frame = read_topic_frame.sort(["account"], ascending=False).head(10)
欢迎光临 51Testing软件测试论坛 (http://bbs.51testing.com/) | Powered by Discuz! X3.2 |