什么是pyQuery
pyquery库是 jQuery 的 Python 实现，能够以jQuery的语法来操作解析 HTML 文档，易用性和解析速度都很好
安装
pip3 install pyquery 注意：由于 pyquery 依赖于 lxml ，要先安装 lxml ，否则会提示失败。
pip3 install lxml PyQuery方法
| 方法名 | 方法实现的结果 |
|---|---|
| .html()和.text() | 获取相应的 HTML 块或者文本内容 |
| selector | 通过选择器来获取目标内容 |
| .eq(index) | 根据索引号获取指定元素（index 从 0 开始） |
| .find() | 查找嵌套元素， |
| .filter() | 根据 class、id 筛选指定元素 |
| .attr() | 获取、修改属性值 |
| item() | 遍历标签 |
案例
from pyquery import PyQuery import requests #pip install lxml class CollegateRank(object): def get_page_data(self,url): response = self.send_request(url=url) if response: # print(response) with open('page.html','w',encoding='gbk') as file: file.write(response) self.parse_page_data(response) def parse_page_data(self,response): # 使用pyquery解析数据 pq = PyQuery(response) # find（）：根据css语法获取标签 # filter（）：根据id或者class过滤标签 ranks = pq.find('div.scores_List dl') ranks = pq.find('div').filter('.scores_List').find('dl') # print(type(ranks.items())) for dl in ranks.items(): # print(dl) school_info = {} school_info['url'] = dl('dt a').eq(0).attr('href') school_info['icon'] = dl('dt a img').attr('src') school_info['name'] =dl('dt strong a').text() school_info['adress'] = dl('dd ul li').eq(0).text() school_info['tese'] = dl('dd ul li').eq(1).find('span').text() school_info['type'] = dl('dd ul li').eq(2).text() school_info['belong'] = dl('dd ul li').eq(3).text() school_info['level'] = dl('dd ul li').eq(4).text() school_info['weburl'] = dl('dd ul li').eq(5).text() print(school_info) def extract_first(self,data=None,defalut=None): if len(data) > 0: return data[0] return defalut def send_request(self, url, headers=None): headers = headers if headers else { 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_13_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.100 Safari/537.36'} response = requests.get(url=url,headers=headers) if response.status_code == 200: return response.text if __name__ == '__main__': url = 'http://college.gaokao.com/schlist/' obj = CollegateRank() obj.get_page_data(url) 来源：51CTO
作者：冷暖自知・・・
链接：https://blog.csdn.net/weixin_43167531/article/details/100708004