from urllib import request
from io import BytesIO
import gzip
import re
#断点调试:F5:进入断点调试 F11:单步执行程序 F5:跳到下一个断点 F11:进入到函数内部
class Spider():
url = 'https://www.douyu.com/g_LOL'
#root_patter = '<div class="DyListCover-content">[\s\S]*?</div>'
root_pattern = '<li class="layout-Cover-item">([\s\S]*?)</li>'
name_pattern = '<div class="DyListCover-userName is-template">([\s\S]*?)</div>'
number_pattern = '</svg>([\s\S]*?)</span>'
def __fetch_content(self):
r = request.urlopen(Spider.url)
#bytes
htmls = r.read()
#以"b’\x1f\x8b\x08"开头的 ,说明它是gzip压缩过的数据,需要先解压缩再转换
htmls = BytesIO(htmls)
htmls= gzip.GzipFile(fileobj=htmls)
#将字节码转化成字符串文本
htmls = htmls.read().decode('utf-8')
#htmls = str(htmls, encoding = 'utf-8')
return htmls
#爬虫分析
#1、选择定位标签(具有唯一性) 2、选择父级的标签作为定位标签
def __analysis(self,htmls):
root_htmls = re.findall(Spider.root_pattern,htmls)
# print(root_htmls[0])
a = 1
#正则分析获取人名和人气观看人数
anchors = []
for html in root_htmls:
name = re.findall(Spider.name_pattern,html)
number = re.findall(Spider.number_pattern,html)
anchor={'name':name,'number':number}
anchors.append(anchor)
#print(anchors)
#print(anchors[0])
return anchors
#数据精炼
def __refine(self,anchors):
l = lambda anchors: {
'name':anchors['name'][0].strip(), #此处报错,数组越界的原因
'number':anchors['number'][0]
}
a = 1
return map(l,anchors)
#排序
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
#数据展示
def __show(self, anchors):
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)
#print(anchors)
spider = Spider()
spider.go()
原生爬虫
最新推荐文章于 2023-07-08 14:15:00 发布
本文介绍了一个Python爬虫项目,通过抓取斗鱼直播平台LOL分区的直播间信息,进行数据提取、分析和展示。首先,使用`urllib`和`gzip`库处理网页内容,然后利用正则表达式匹配主播名称和观看人数。接着,对数据进行精炼和排序,最后展示排序后的主播人气排名。整个过程涉及网页内容的解压、解析、数据提取和排序等关键步骤。
摘要由CSDN通过智能技术生成