import urllib.request
from urllib.parse import quote
import string

class HtmlDownloader(object):
???
???
??? def download(self,url):
??????? if url is None:
??????????? return None
??????? s=quote(url,safe=string.printable)
???????
??????? response=urllib.request.urlopen(s)
??????? if response.getcode()!=200:
??????????? return None
??????? return response.read()

urllib.quote 解決Python傳遞中文參數(shù)給URL

def?_get_new_urls(self,?page_url,?soup):
????new_urls?=?set()
????#<a?target="_blank"?href="/item/%E9%98%BF%E5%A7%86%E6%96%AF%E7%89%B9%E4%B8%B9/2259975"?data-lemmaid="2259975">阿姆斯特丹</a>
????#https:?//?baike.baidu.com?/?item?/?阿姆斯特丹?/?2259975
????links?=?soup.find_all('a',href=re.compile(r"/item/"))
????for?link?in?links:
????????new_url?=?'/item/'+link.get_text()
????????new_full_url?=?urlparse.urljoin(page_url,new_url)
????????new_urls.add(new_full_url)
????return?new_urls

我也是這么寫的，有哪里寫錯(cuò)了嗎？

這一步務(wù)必使用函數(shù)進(jìn)行url的拼接,帶有中文的url會(huì)有編碼問題