我是scrapy和python的新手,我能够从URL获取详细信息,我想输入链接并下载所有文件(.htm和.txt)。
我的代码
import scrapy
class legco(scrapy.Spider):
name = "sec_gov"
start_urls = ["https://www.sec.gov/cgi-bin/browse-edgar?company=&match=&CIK=&filenum=&State=&Country=&SIC=2834&owner=exclude&Find=Find+Companies&action=getcompany"]
def parse(self, response):
for link in response.xpath('//table[@summary="Results"]//td[@scope="row"]/a/@href').extract():
absoluteLink = response.urljoin(link)
yield scrapy.Request(url = absoluteLink, callback = self.parse_page)
def parse_page(self, response):
for links in response.xpath('//table[@summary="Results"]//a[@id="documentsbutton"]/@href').extract():
targetLink = response.urljoin(links)
yield {"links":targetLink}
我需要进入链接并下载所有以.htm和.txt文件结尾的文件。下面的代码不起作用。
if link.endswith('.htm'):
link = urlparse.urljoin(base_url, link)
req = Request(link, callback=self.save_pdf)
yield req
def save_pdf(self, response):
path = response.url.split('/')[-1]
with open(path, 'wb') as f:
f.write(response.body)
有人可以帮助我吗?预先感谢。
答案 0 :(得分:0)
请尝试以下操作以将文件下载到您的桌面或脚本中提到的任何位置:
import scrapy, os
class legco(scrapy.Spider):
name = "sec_gov"
start_urls = ["https://www.sec.gov/cgi-bin/browse-edgar?company=&match=&CIK=&filenum=&State=&Country=&SIC=2834&owner=exclude&Find=Find+Companies&action=getcompany"]
def parse(self, response):
for link in response.xpath('//table[@summary="Results"]//td[@scope="row"]/a/@href').extract():
absoluteLink = response.urljoin(link)
yield scrapy.Request(url = absoluteLink, callback = self.parse_links)
def parse_links(self, response):
for links in response.xpath('//table[@summary="Results"]//a[@id="documentsbutton"]/@href').extract():
targetLink = response.urljoin(links)
yield scrapy.Request(url = targetLink, callback = self.collecting_file_links)
def collecting_file_links(self, response):
for links in response.xpath('//table[contains(@summary,"Document")]//td[@scope="row"]/a/@href').extract():
if links.endswith(".htm") or links.endswith(".txt"):
baseLink = response.urljoin(links)
yield scrapy.Request(url = baseLink, callback = self.download_files)
def download_files(self, response):
path = response.url.split('/')[-1]
dirf = r"C:\Users\WCS\Desktop\Storage"
if not os.path.exists(dirf):os.makedirs(dirf)
os.chdir(dirf)
with open(path, 'wb') as f:
f.write(response.body)
为清楚起见:您需要明确指定dirf = r"C:\Users\WCS\Desktop\Storage"
,其中C:\Users\WCS\Desktop
或其他内容将是您想要的位置。但是,该脚本将自动创建Storage
文件夹以将其中的文件保存在其中。