MCPcopy
hub / github.com/DropsDevopsOrg/ECommerceCrawlers / save_size_txt

Method save_size_txt

SohuNewCrawler/export_article.py:54–85  ·  view source on GitHub ↗
(self)

Source from the content-addressed store, hash-verified

52
53 return False
54 def save_size_txt(self):
55
56 if not self.save_file_name:
57 file_name = str(time.time()) + uuid()
58 self.save_file_name = os.path.join(self.save_path, file_name + '.txt')
59 while True:
60 if self.ds < self.file_size:
61 article = ma.select_one_update() # 导出数据库信息的方式
62 if not article:
63 self.errMessage.put('【导出文件】文件保存结束')
64 self.errMessage.put(1)
65 print('新闻导出完成')
66 print('没有最新的消息')
67 break
68 p = article.get('article')
69
70 leng_p_list =p.split('\n')
71 with open(self.save_file_name, 'a+', encoding='utf-8')as f:
72 for leng_p in leng_p_list:
73 if len(leng_p)>=self.length_p:
74 f.write(leng_p)
75 f.write('\n')
76 else:
77 print('300k文件写完')
78 self.errMessage.put("【导出文件】文件保存{}kb".format(self.ds/1000))
79 self.ds = 0
80 file_name = str(time.time()) + uuid()
81 self.save_file_name=os.path.join(self.save_path, file_name + '.txt')
82 with open(self.save_file_name, 'a+', encoding='utf-8')as f:
83 f.write('')
84 self.ds = os.path.getsize(self.save_file_name)
85 print('正在写入数据大小{}kb'.format( self.ds/1000))
86
87 def run(self,input_path,errMessage):
88 self.errMessage=errMessage

Callers 1

runMethod · 0.95

Calls 2

getMethod · 0.80
select_one_updateMethod · 0.45

Tested by

no test coverage detected