我用python爬下来网址怎么带个括号和单引号啊

我用python爬下来网址怎么带个括号和单引号啊

我看别人最后都是一串一串网址没有【】和''的

from bs4 import BeautifulSoup

import re

import urllib.request, urllib.error

import sqlite3

def main():

baseurl = "http://www.prnasia.com/m/mediafeed/rss?id=2303&t=240"

datalist = getData(baseurl)

savepath = ".\wenjian"

saveData(savepath)

findLink = re.compile('<a href="https://q.cnblogs.com/q/130354/(.*?)" target="_blank">')

def getData(baseurl):

datalist = []

# html= askUrl("http://www.prnasia.com/m/mediafeed/rss?id=2303&t=240")

# for i in range(0,1):

url = baseurl

html = askUrl(url)

soup = BeautifulSoup(html, "html.parser")

for presscolumn in soup.find_all('div', class_="presscolumn"):

data = []

item = str(presscolumn)

link = re.findall(findLink, item)

print(link)

data.append(link)

return datalist

def askUrl(url):

head = {

"User-Agent": "Mozilla/5.0(Windows NT 10.0; Win64; x64)AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36"

}

request = urllib.request.Request(url, headers=head)

html = ""

try:

response = urllib.request.urlopen(request)

html = response.read().decode("utf-8")

# print(html)

except urllib.error.URLError as e:

if hasattr(e, "code"):

print(e.code)

if hasattr(e, "reason"):

print(e.reason)

return html

def saveData(savepath):

print("save....")

if name == "main":

main()

回答

python">import requests
from lxml import etree
url = 'http://www.prnasia.com/m/mediafeed/rss?id=2303&t=240'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/87.0.4280.66 Safari/537.36'
}
res = requests.get(url, headers=headers)
res_dome = etree.HTML(res.text)
print(res_dome.xpath('//h3/a/@href'))

以上是 我用python爬下来网址怎么带个括号和单引号啊 的全部内容， 来源链接： utcz.com/a/68856.html

回到顶部