断点调试

class Spider():
url=‘https://www.panda.tv/cate/lol’
root_pattern=’

[\s\S]?

‘
name_pattern=’([\s\S]?)‘
num_pattern=’([\s\S]*?)'
def __fetch_content(self):
r=request.urlopen(Spider.url)
htmls=r.read()
htmls=str(htmls, encoding=‘utf-8’)
return htmls
def __analysis(self,htmls):
root_html=re.findall(Spider.root_pattern,htmls)
anchors=[]
for html in root_html:
name=re.findall(Spider.name_pattern,html)
number=re.findall(Spider.num_pattern,html)
anchor={‘Name’:name,‘Number’:number}
anchors.append(anchor)
return anchors

def __refine(self,anchors):
    l = lambda anchor: {
        'Name':anchor['Name'][0].strip(),
        'Number':anchor['Number'][0]
        }
    return map(l, anchors)

def go(self):
    htmls=self.__fetch_content()
    anchors=self.__analysis(htmls)
    anchors=list(self.__refine(anchors))
    print(anchors)

spider=Spider()
spider.go()

写回答

1回答