Question

之前我被问过这个问题，但仍然没有得到解决方案，我在网上搜索就像没有人遇到过同样的问题。我有安装错误的xlwt吗？或者json有什么不对劲？有人能帮助我吗？我是python的新手。非常感谢！ KeyError：＆＃39; content＆＃39;

# -*- coding:utf-8 -*-
import requests
import time
import random
import xlwt
import json

def post_request(url=None, para={}, headers={}):
    print 'Downloading: ' + str(para['pn'])
    req = requests.post(url, data=para, headers=headers)
    return req

if __name__ == '__main__':
    url = 'https://www.lagou.com/jobs/positionAjax.json?needAddtionalResult=false&isSchoolJob=0'
    headers = {
        'Host':'www.lagou.com',
        'Referer':'https://www.lagou.com/jobs/list_%E6%95%B0%E6%8D%AE%E5%88%86%E6%9E%90?labelWords=&fromSearch=true&suginput',
        'User-Agent':'Mozilla/5.0 (Linux; Android 6.0; Nexus 5 Build/MRA58N) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.96 Mobile Safari/537.36'
    }

    pn = 1
    end = 31
    for x in range(pn, end, 1):
        para = {
            'first': 'true',
            'kd': 'Python',
            'pn': pn
        }
        req = post_request(url, para, headers)
        path = 'd://PyCharmProject//lagou_scraping//Python_search_result//'
        f = open(path + para['kd'] + '-' + str(para['pn']) + '.json', 'wb')
        f.write(req.content)
        f.close()
        time.sleep(random.randint(3, 8))
        pn = pn + 1
def read_json(path):
    f = open(path)
    dictory = json.load(f, encoding='utf-8')
    return dictory

if __name__ == '__main__':
    xls = xlwt.Workbook()
    sheet = xls.add_sheet('native')
    sheet.write(0, 0, 'positionName')
    sheet.write(0, 1, 'salary')
    sheet.write(0, 2, 'education')
    sheet.write(0, 3, 'workYear')
    sheet.write(0, 4, 'city')
    sheet.write(0, 5, 'companyShortName')
    sheet.write(0, 6, 'companySize')
    sheet.write(0, 7, 'financeStage')
    sheet.write(0, 8, 'industryField')
    sheet.write(0, 9, 'jobNature')
    sheet.write(0, 10, 'companyLogo')

    sheetPosition = {'row':1, 'col':0}
    pn = 1
    for x in range(pn, 31, 1):
        path = 'd://PyCharmProject//lagou_scraping//Python_search_result//Python-' + str(pn) + '.json'
        dictory = read_json(path)
        row = sheetPosition['row']
        col = sheetPosition['col']
        pn = pn + 1
        for x in dictory['content']['positionResult']['result']:
            sheet.write(row, col, x['positionName']) # 0
            col = col + 1
            sheet.write(row, col, x['salary']) # 1
            col = col + 1
            sheet.write(row, col, x['education']) # 2
            col = col + 1
            sheet.write(row, col, x['workYear']) # 3
            col = col + 1
            sheet.write(row, col, x['city']) # 4
            col = col + 1
            sheet.write(row, col, x['companyShortName']) # 5
            col = col + 1
            sheet.write(row, col, x['companySize']) # 6
            col = col + 1
            sheet.write(row, col, x['financeStage']) # 7
            col = col + 1
            sheet.write(row, col, x['industryField']) # 8
            col = col + 1
            sheet.write(row, col, x['jobNature']) # 9
            col = col + 1
            sheet.write(row, col, x['companyLogo']) # 10
            col = col + 1

            col = 0
            row = row + 1
            sheetPosition = {'row': row, 'col': col}
    xls.save('d://PyCharmProject//lagou_scraping//lagou_python.xls')

Answer 1

好像你的错误来自这里：

 f = open(path + para['kd'] + '-' + str(para['pn']) + '.json', 'wb')
    f.write(req.content) # <-- Here is the probable error.
    f.close()

也许您必须先检查状态代码或尝试阻止抓住错误：

#using status code 200
#some server may return different status code 
#other than 200, check how the server return on success
if(req.status_code == 200):
   #now you're ok to resume with your code above
else:
   #since you're in the for loop, skip this iteration
   pass

我希望这会有所帮助。

有关python keyerror的错误

1 个答案: