百度贴吧

]】】；；；；
；】；；；；；；；；；；；
import requests
import re
import urllib.parse
import os

class TieBaSpider():

def __init__(self):
    self.url = 'https://tieba.baidu.com/f?kw={}&pn={}'

    self.name = 'tieba'
    if not os.path.exists(self.name):
        os.mkdir(self.name)

def send_request(self, full_url):
    response = requests.get(full_url)
    if response.status_code == 200:
       content = response.content
    return content
    else:
        print('出错乱了')

def parse_content(self, content):
    content = content.decode('utf8')
    pattern = re.compile('<a rel="noreferrer" href="(/p.*?)"', re.S)
    hrefs = pattern.findall(content)

    for href in hrefs:
        detail = urllib.parse.urljoin(self.url, href)
        content = self.send_request(detail)

        self.parse_detail_content(content)

def parse_detail_content(self, content):
    content = content.decode('utf8')
    pattern = re.compile('<img\sclass="BDE Image"\ssrc="(.*?)"')
    imgs = pattern.findall(content)

    for img in imgs:
        content = self.send_request(img)
        self.save_content(content, img)

def save_content(self, content, img):
    img_name = img[-15:]
    print('正在保存%s' % img_name)
    with open(self.name + '/' + img_name, 'wb') as f:
        f.write(content)

def start(self):
    kw = input('输入贴吧的名字')
    page = int(input('请输人爬多少页'))
    for i in range(1, page + 1):
        pn = (i - 1) * 50
        full_url = self.url.format(kw, pn)
        content = self.send_request(full_url)
        self.parse_content(content)

if name == ‘main’:
tbs = TieBaSpider()
tbs.start()···············