weixin_43473864的博客

from bs4 import BeautifulSoup import requests def one(url): r = requests.get(url, allow_redirects = False) fin = r.text soup = BeautifulSoup(fin,'html.parser') comments = soup.find('d...

from bs4 import BeautifulSoup import requests from lxml import etree import re def get_url(url): r = requests.get(url) text = r.text #使用etree.HTML处理源代码，然后使用Xpath提取内容 html = etree.HTML(...

读取excel # 读取excel worksheet = xlrd.open_workbook(filepath) table = worksheet.sheet_by_index(1)#读取第一个sheet里面的类容 datas=[] # 第一行和第二行的内容不读入 for i in range(table.nrows): if i == 0: continue ...

这篇文章是做数据处理时输出的数据 from collections import defaultdict def get_count(fPath): invertedIndex = defaultdict(list) docNumber = 0 text=[] with open(fPath, 'r',encoding='utf-8') as f: ...

#保存为pickle文件 pipe_path='pipe_feature_nb_all.pkl' with open(pipe_path,'wb') as fw: pickle.dump(Pipe,fw) #加载pickle文件 pipe=pickle.load(open('pipe_feature_dt_all.pkl','rb'))

with open('/Users/ronald/Downloads/Archive/resume.json','r') as f: cvResult = f.readlines() import json for c in cvResult: if (json.loads(c)['job_id']['$oid']) == '5bd30948f7bf070001464815':...