import scrapy
from scrapy.http import Request
from bs4 import BeautifulSoup
class TestSpider(scrapy.Spider):
name = 'test'
start_urls = ['https://www.baroul-bucuresti.ro/index.php?urlpag=tablou-definitivi&p=1']
def parse(self, response):
base_url='https://www.baroul-bucuresti.ro'
soup=BeautifulSoup(response.text, 'html.parser')
tra = soup.find_all('div',class_='panel-title')
productlinks=[]
for links in tra:
for link in links.find_all('a',href=True)[1:]:
comp=base_url+link['href']
yield Request(comp, callback=self.parse_book)
d1=''
def parse_book(self, response):
title=response.xpath("//h1//text()").get()
detail=response.xpath("//div[@class='av_bot_left left']//p")
for i in range(len(detail)):
if 'Decizia de intrare:' in detail[i].get():
d1=response.xpath("//em[@class='ral_i']//text()").get()
print(d1)
它们将提供以下输出:
Decizia de intrare:
但我想要的实际输出是这些,正如您在网站https://www.baroul-bucuresti.ro/avocat/15655/aanegroae-ana-maria的页面下看到的:
Decizia de intrare: 2469/1-06.12.16
1条答案
按热度按时间zbq4xfa01#
请尝试以下操作:
在if语句中,我没有使用根节点的xpath,而是使用了已经确定为包含所需文本的节点的xpath,然后我只是进行了一些字符串格式化。