用scrapy爬取网易新闻时出错[新手]

Question

items.py import scrapy class News163Item(scrapy.Item): title = scrapy.Field() url = scrapy.Field() source = scrapy.Field() content = scrapy.Field() news_spider.py #coding:utf-8 from scrapy.contrib.linkextractors import LinkExtractor from scrapy.contrib.spiders import CrawlSpider,Rule class ExampleSpider(CrawlSpider): name = "news" allowed_Domains = ["news.163.com"] start_urls = ['http://news.163.com/'] rules = [ Rule(LinkExtractor(allow=r"/14/12\d+/\d+/*"), 'parse_news') ] def parse_news(self,response): news = News163Item() news['title'] = response.xpath("//*[@id="h1title"]/text()").extract() news['source'] = response.xpath("//*[@id="ne_article_source"]/text()").extract() news['content'] = response.xpath("//*[@id="endText"]/text()").extract() news['url'] = response.url return news cd进入所在目录后，命令行执行： scrapy crawl news -o news163.json 会跳出如下错误： Traceback (most recent call last): File "/usr/bin/scrapy", line 9, in <module> load_entry_point('Scrapy==0.24.4', 'console_scripts', 'scrapy')() File "/usr/lib/pymodules/python2.7/scrapy/cmdline.py", line 143, in execute _run_print_help(parser, _run_command, cmd, args, opts) File "/usr/lib/pymodules/python2.7/scrapy/cmdline.py", line 89, in _run_print_help func(*a, **kw) File "/usr/lib/pymodules/python2.7/scrapy/cmdline.py", line 150, in _run_command cmd.run(args, opts) File "/usr/lib/pymodules/python2.7/scrapy/commands/crawl.py", line 57, in run crawler = self.crawler_process.create_crawler() File "/usr/lib/pymodules/python2.7/scrapy/crawler.py", line 87, in create_crawler self.crawlers[name] = Crawler(self.settings) File "/usr/lib/pymodules/python2.7/scrapy/crawler.py", line 25, in __init__ self.spiders = spman_cls.from_crawler(self) File "/usr/lib/pymodules/python2.7/scrapy/spidermanager.py", line 35, in from_crawler sm = cls.from_settings(crawler.settings) File "/usr/lib/pymodules/python2.7/scrapy/spidermanager.py", line 31, in from_settings return cls(settings.getlist('SPIDER_MODULES')) File "/usr/lib/pymodules/python2.7/scrapy/spidermanager.py", line 22, in __init__ for module in walk_modules(name): File "/usr/lib/pymodules/python2.7/scrapy/utils/misc.py", line 68, in walk_modules submod = import_module(fullpath) File "/usr/lib/python2.7/importlib/__init__.py", line 37, in import_module __import__(name) File "/home/gao/news/news/spiders/news_spider.py", line 15 news['title'] = response.xpath("//*[@id="h1title"]/text()").extract() ^ SyntaxError: invalid syntax 请问是哪里出错了？python新手，scrapy也是最近才用的，很生疏，求指点。 谢谢：@捏造的信仰 的回答,但是更改过之后，还是有错误。 2014-12-02 20:13:02+0800 [news] ERROR: Spider error processing <GET http://lady.163.com/14/1201/09/ACCAN4MB002649P6.html> Traceback (most recent call last): File "/usr/lib/python2.7/dist-packages/twisted/internet/base.py", line 824, in runUntilCurrent call.func(*call.args, **call.kw) File "/usr/lib/python2.7/dist-packages/twisted/internet/task.py", line 638, in _tick taskObj._oneWorkUnit() File "/usr/lib/python2.7/dist-packages/twisted/internet/task.py", line 484, in _oneWorkUnit result = next(self._iterator) File "/usr/lib/pymodules/python2.7/scrapy/utils/defer.py", line 57, in <genexpr> work = (callable(elem, *args, **named) for elem in iterable) --- <exception caught here> --- File "/usr/lib/pymodules/python2.7/scrapy/utils/defer.py", line 96, in iter_errback yield next(it) File "/usr/lib/pymodules/python2.7/scrapy/contrib/spidermiddleware/offsite.py", line 26, in process_spider_output for x in result: File "/usr/lib/pymodules/python2.7/scrapy/contrib/spidermiddleware/referer.py", line 22, in <genexpr> return (_set_referer(r) for r in result or ()) File "/usr/lib/pymodules/python2.7/scrapy/contrib/spidermiddleware/urllength.py", line 33, in <genexpr> return (r for r in result or () if _filter(r)) File "/usr/lib/pymodules/python2.7/scrapy/contrib/spidermiddleware/depth.py", line 50, in <genexpr> return (r for r in result or () if _filter(r)) File "/usr/lib/pymodules/python2.7/scrapy/contrib/spiders/crawl.py", line 67, in _parse_response cb_res = callback(response, **cb_kwargs) or () File "/home/gao/news/news/spiders/news_spider.py", line 14, in parse_news news = News163Item() exceptions.NameError: global name 'News163Item' is not defined 请问这又是什么原因呢？

Answer 1

字符串外部使用的是双引号，在双引号内部还需要使用引号的话可以使用单引号。例如

news['title'] = response.xpath("//*[@id='h1title']/text()").extract()

Answer 2

字符串中的引号没有转码导致的语法错误。应该改为

news['title'] = response.xpath("//*[@id=\"h1title\"]/text()").extract()

下面几行也是的。

Answer 3

你需要做的是导包"
from 你的项目名称.items import News163Item