爬虫前奏:
- 明确目的,找到数据对应的网页,分析网页的结构找到数据s所在的标签位置
- 模拟Http请求,向服务器发送这个请求,获取到服务器返回我们的html
- 用正则表达式提取我们要的数据(名字、人气)
import re
from urllib import request
# 断点调试
# BeautifulSoup scrapy
# 爬虫、反爬虫、反反爬虫
# ip封
# 代理ip库
class Spider():
url = 'https://www.panda.tv/cate/lol'
root_pattern = '<div cass="video-info">([\s\S]*?)</div>' #正则匹配: 组() 贪婪模式
name_pattern = '</i>([\s\S]*?)</span>'
number_pattern = '<span cass="video-number">([\s\S]*?)</span>'
# 获取内容
def __fetch_content(self):
r = request.urlopen(Spider.url)
htmls = r.read()
htmls = str(htmls, encoding='utf-8')
return htmls
# 分析数据
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.number_pattern, html)
anchor = {'name': name, 'number': number}
anchors.append(anchor)
return anchors
# 数据精炼
def __refine(self, anchors):
l = lambda anchor: {
'name': anchor['name'][0].strip(), # 去除空格和换行符
'number': anchor['number'][0]
}
return map(l, anchors)
def __sort(self, anchors):
anchors = sorted(anchors, key = self.__sort_seed, reverse=True)
return anchors
def __sort_seed(self, anchor):
r = re.findall('\d*', anchor['number'])
number = float(r[0])
if '万' in anchor['number']:
number *= 10000
return number
def __show(self, anchors):
# for anchor in anchors:
# print(anchor['name']+ '----' + anchor['number'])
for rank in range(0, len(anchors)):
print('rank '+ str(rank + 1)
+ ' : ' + anchors[rank]['name']
+ ' ' + anchors[rank]['number'])
def go(self):
htmls = self.__fetch_content()
anchors = self.__analysis(htmls)
anchors = list(self.__refine(anchors))
anchors = self.__sort(anchors)
self.__show(anchors)
spider = Spider()
spider.go()
网友评论