python scrapy 表单post rest api接口返回json写wordpress
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 | import scrapy import json from urllib.parse import urlencode from scrapy.crawler import CrawlerProcess from scrapy import Spider, FormRequest from wordpress_xmlrpc import Client, WordPressPost from wordpress_xmlrpc.methods.posts import NewPost id = 'username' password = 'pwd' publish_url = 'http://wordpress.url/xmlrpc.php' source_url = 'http://gubatopic.eastmoney.com/interface/GetData.aspx' post_data = { "param" : "ps%3D7%26p%3D1%26type%3D0" , "path" : "newtopic%2Fapi%2FTopic%2FHomePageListRead" , "env" : "2" } class EmSpider(Spider): name = "em" def start_requests( self ): yield FormRequest(source_url, formdata = post_data) def parse( self ,response): for item in json.loads(response.text)[ 're' ]: print (item[ 'nickname' ] + ' ,' + str (item[ 'htid' ])) wp = Client(publish_url, id , password) post = WordPressPost() post.post_status = 'publish' post.title = item[ 'nickname' ] post.content = str (item[ 'htid' ]) #post.excerpt = '这里是摘抄样式示例' post.terms_names = { "post_tag" : [ 'Python' ], "category" : [ 'Python' ] } wp.call(NewPost(post)) |
【推荐】编程新体验,更懂你的AI,立即体验豆包MarsCode编程助手
【推荐】凌霞软件回馈社区,博客园 & 1Panel & Halo 联合会员上线
【推荐】抖音旗下AI助手豆包,你的智能百科全书,全免费不限次数
【推荐】博客园社区专享云产品让利特惠,阿里云新客6.5折上折
【推荐】轻量又高性能的 SSH 工具 IShell:AI 加持,快人一步