def extract_results(self, response):
selector = Selector(response.text)
for item in selector.css('li.b_algo'):
title = item.css('h2>a')[0].text.strip()
text = None
span = item.css('div.b_caption>p')
if len(span) > 0:
text = span[0].text.strip()
url = item.css('h2>a')[0].attr('href').strip()
if text is not None:
yield {'title': title, 'text': text, 'url': url}
def extract_results(self, response):
selector = Selector(response.text)
for item in selector.css('div.g'):
title = item.css('h3')[0].text.strip()
text = None
span_st = item.css('span.st')
if len(span_st) > 0:
text = span_st[0].text.strip()
url = item.css('div.r>a')[0].attr('href').strip()
if text is not None:
yield {'title': title, 'text': text, 'url': url}
def extract_results(self, response):
selector = Selector(response.text)
for item in selector.css('div.result'):
title = item.css('h3>a')[0].text.strip()
text = None
abstract = item.css('div.c-abstract')
if len(abstract) > 0:
text = abstract[0].text.strip()
url = item.css('h3>a')[0].attr('href').strip()
if text is not None:
yield {'title': title, 'text': text, 'url': url}
def extract_results(self, response):
selector = Selector(response.text)
for item in selector.css('li.algo-result'):
title = item.css('a.algo-title')[0].text.strip()
text = None
span = item.css('span.algo-summary')
if len(span) > 0:
text = span[0].text.strip()
url = item.css('a.algo-title')[0].attr('href').strip()
if text is not None:
yield {'title': title, 'text': text, 'url': url}
def extract_results(self, response):
selector = Selector(response.text)
for item in selector.css('div.algo-sr'):
title = item.css('h3>a')[0].text.strip()
text = None
p_lh_l = item.css('p.lh-l')
if len(p_lh_l) > 0:
text = p_lh_l[0].text.strip()
url = item.css('h3>a')[0].attr('href').strip()
url = unquote(self.yahoo_url_reg.search(url).group(1))
if text is not None:
yield {'title': title, 'text': text, 'url': url}
def extract_results(self, response):
selector = Selector(response.text)
for item in selector.css('li.reItem'):
a = item.css('h2>a')
if len(a) <= 0:
continue
title = a[0].text.strip()
text = None
div = item.css('div.reNewsWrapper')
if len(div) > 0:
text = div[0].text.strip().split('\n')[0]
url = urljoin('http://www.chinaso.com/search/',
item.css('h2>a')[0].attr('href').strip())
if text is not None:
yield {'title': title, 'text': text, 'url': url}
def parse(self, response):
selector = Selector(response.text)
for quote in selector.xpath('//div[@class="quote"]'):
text = quote.xpath('.//span[@itemprop="text"]')[0].text
author = quote.xpath('.//small[@itemprop="author"]')[0].text
author_url = quote.xpath('.//span/a/@href')[0].text
author_url = urljoin(str(response.url), author_url)
tags = quote.xpath('.//div[@class="tags"]/a').text
self.log(
'quote: %s',
dict(text=text,
tags=tags,
author=author,
author_url=author_url))
next_page_url = selector.xpath('//li[@class="next"]/a/@href')[0].text
self.log('next page url: %s', next_page_url)
def parse(self, response):
selector = Selector(response.text)
for quote in selector.css('div.quote'):
text = quote.css('span.text')[0].text
author = quote.css('small.author')[0].text
author_url = quote.css('small+a')[0].attr('href')
author_url = urljoin(str(response.url), author_url)
tags = quote.css('div.tags a').text
self.quotes.append(
dict(text=text,
tags=tags,
author=author,
author_url=author_url))
next_page = selector.css('li.next a')
if len(next_page) > 0:
next_page_url = urljoin(str(response.url),
next_page[0].attr('href'))
yield HttpRequest(next_page_url, callback=self.parse)
def extract_results(self, response):
selector = Selector(response.text)
for item in selector.css('li.res-list'):
title = item.css('h3>a')[0].text.strip()
text = None
res_desc = item.css('p.res-desc')
if len(res_desc) > 0:
text = res_desc[0].text.strip()
else:
res_rich = item.css('div.res-rich')
if len(res_rich) > 0:
text = res_rich[0].text.strip()
h3_a = item.css('h3>a')[0]
url = h3_a.attr('data-url')
if not url:
url = h3_a.attr('href').strip()
if text is not None:
yield {'title': title, 'text': text, 'url': url}
def extract_results(self, response):
selector = Selector(response.text)
for item in selector.css('div.vrwrap,div.rb'):
h = item.css('h3>a')
if len(h) <= 0:
continue
title = h[0].text.strip()
text = None
div_ft = item.css('div.ft')
if len(div_ft) > 0:
text = div_ft[0].text.strip()
else:
p_str = item.css('p.str_info')
if len(p_str) > 0:
text = p_str[0].text.strip()
url = urljoin('https://www.sogou.com/', item.css('h3>a')[0].attr('href').strip())
if text is not None:
yield {'title': title, 'text': text, 'url': url}
def parse(self, response):
selector = Selector(response.text)
hot = selector.css("div.hotnews a").text
self.log("Hot News:")
for i in range(len(hot)):
self.log("%s: %s", i + 1, hot[i])
async def parse(self, response):
selector = Selector(response.text)
tags = selector.xpath("//div[contains(@class, 'tags-box')]//a").text
self.log("Top ten tags: %s", tags)
yield HttpRequest("http://quotes.toscrape.com/", callback=self.parse)
<a href="/author/J-K-Rowling">(about)</a>
</span>
<div class="tags">
Tags:
<a class="tag" href="/tag/abilities/page/1/">abilities</a>
<a class="tag" href="/tag/choices/page/1/">choices</a>
</div>
</div>
</body>
</html>
'''
if __name__ == '__main__':
from xpaw import Selector
selector = Selector(text)
print('# CSS Selector, content of quotes:')
for quote in selector.css('div.quote'):
print(quote.css('span.text')[0].text)
print('# XPath, content of quotes:')
for quote in selector.xpath('//div[@class="quote"]'):
print(quote.xpath('.//span[@class="text"]')[0].text)
print('# CSS Selector, content of quotes, with HTML tags:')
for quote in selector.css('div.quote'):
print(quote.css('span.text')[0].string)
print('# CSS Selector, quote tags')
for quote in selector.css('div.quote'):
def parse_results(engine, resp):
res = []
selector = Selector(resp.text)
if engine == 'Google':
if 'google.com.hk/sorry/' in resp.url:
raise ServiceBanError
topstuff = selector.css('#topstuff').text
if len(topstuff) > 0 and '未找到符合' in topstuff[0]:
pass
else:
for item in selector.css('div.g'):
try:
title = item.css('h3')[0].text.strip()
text = None
span_st = item.css('span.st')
if len(span_st) > 0:
text = span_st[0].text.strip()
url = item.css('div.r>a')[0].attr('href').strip()
if text is not None:
res.append({'title': title, 'text': text, 'url': url})
except Exception:
pass
elif engine == 'Yahoo':
for item in selector.css('div.algo-sr'):
try:
title = item.css('h3>a')[0].text.strip()
text = None
p_lh_l = item.css('p.lh-l')
if len(p_lh_l) > 0:
text = p_lh_l[0].text.strip()
url = item.css('h3>a')[0].attr('href').strip()
url = unquote(yahoo_url_reg.search(url).group(1))
if text is not None:
res.append({'title': title, 'text': text, 'url': url})
except Exception:
pass
elif engine == 'Ask':
for item in selector.css('li.algo-result'):
try:
title = item.css('a.algo-title')[0].text.strip()
text = None
span = item.css('span.algo-summary')
if len(span) > 0:
text = span[0].text.strip()
url = item.css('a.algo-title')[0].attr('href').strip()
if text is not None:
res.append({'title': title, 'text': text, 'url': url})
except Exception:
pass
elif engine == 'Bing':
for item in selector.css('li.b_algo'):
try:
title = item.css('h2>a')[0].text.strip()
text = None
span = item.css('div.b_caption>p')
if len(span) > 0:
text = span[0].text.strip()
url = item.css('h2>a')[0].attr('href').strip()
if text is not None:
res.append({'title': title, 'text': text, 'url': url})
except Exception:
pass
return res
def parse(self, response):
selector = Selector(response.text)
for quote in selector.css('div.quote'):
text = quote.css('span.text')[0].text
author = quote.css('small.author')[0].text
self.log(author + ": " + text)