求问运行失败原因?
(本人的Python为3.4版本)听了两遍老师的课后,自己默写了一遍代码出来,但是运行报错,出错行如下:
from baike_spider import url_manager, html_downloader, html_parser, html_outputer
报错原因是句法错误:EOF while scanning triple-quoted string literal
# -*- coding:utf-8 -*-
from baike_spider import url_manager, html_downloader, html_parser, html_outputer
class SpiderMain(object):
def __init__(self):
self.urls = url_manager.UrlManager()
self.downloader =html_downloader.HtmlDownloader()
self.parser = html_parser.HtmlParser()
self.outputer = html_outputer.HtmlOutputer()
def craw(self, root_url):
count = 1
self.urls.add_new_url(root_url)
while self.urls.has_new_url():
try:
new_url = self.urls.get_new_url()
print ("crawling URL => %s ...:%s" % (count, new_url))
html_cont = self.downloader.download(new_url)
new_urls, new_data = self.parser.parse(new_url, html_cont)
self.urls.add_new_urls(new_urls)
self.outputer.collect_data(new_data)
if count == 1000:
break
count = count + 1
except:
print ('craw failed')
self.outputer.outputer_html()
if __name__=="__main__":
root_url = "http://http://baike.baidu.com/item/Python"
obj_spider = SpiderMain()
obj_spider.craw(root_url)P.s. 之前还经历过编码错误,所以加上了第一行代码