link_1999
/
crawler-MiniProgram
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

上传文件至 'dagongPro/spiders' 

新增：将新闻标题、发布单位、发布日期、正文内容添加到MySQL数据库功能
This commit is contained in:
link_1999 2022-04-06 20:15:47 +08:00
parent 700db04c9c
commit eace6a5c13
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
dagongPro/spiders/dagong.py
View File

@ -18,7 +18,7 @@ class DagongSpider(scrapy.Spider):
def parse(self, response): def parse(self, response):
li_list = response.xpath('/html/body/div[2]/div/div[2]/ul[2]/li[2]/div/ul/li') li_list = response.xpath('/html/body/div[2]/div/div[2]/ul[2]/li[2]/div/ul/li')
alist = [6] # [0内地, 2香港, 4两岸, 6国际, 8军事] alist = [8] # [0内地, 2香港, 4两岸, 6国际, 8军事]
for index in alist: for index in alist:
model_url = li_list[index].xpath('./a/@href').extract_first() model_url = li_list[index].xpath('./a/@href').extract_first()
self.models_urls.append(model_url) self.models_urls.append(model_url)
@ -34,7 +34,7 @@ class DagongSpider(scrapy.Spider):
name = div.xpath('./dd[1]/a/text()').extract_first() name = div.xpath('./dd[1]/a/text()').extract_first()
# 取出标题中的特殊字符 # 取出标题中的特殊字符
title = re.sub(u"\\(.*?\\)|\\{.*?}|\\[.*?]|\\*.*?|\\:.*?|\\/.*?|\\\".*?|\\\\.*?|\\?.*?", "", name) title = re.sub(u"\\(.*?\\)|\\{.*?}|\\[.*?]|\\*.*?|\\:.*?|\\/.*?|\\\".*?|\\\\.*?|\\?.*?\\|.*?", "", name)
new_detail_url = div.xpath('./dd[1]/a/@href').extract_first() new_detail_url = div.xpath('./dd[1]/a/@href').extract_first()
# print(title) # print(title)
@ -50,6 +50,7 @@ class DagongSpider(scrapy.Spider):
title = response.xpath('//div[@class="wrap_left"]/h2/text()').extract_first() title = response.xpath('//div[@class="wrap_left"]/h2/text()').extract_first()
content = response.xpath('//div[@class="wrap_left"]/div[3]//text()').extract() content = response.xpath('//div[@class="wrap_left"]/div[3]//text()').extract()
content = ''.join(content) content = ''.join(content)
print(content)
date = response.xpath('//div[@class="wrap_left"]/div[1]/div[1]//text()').extract() date = response.xpath('//div[@class="wrap_left"]/div[1]/div[1]//text()').extract()
date = ''.join(date) date = ''.join(date)