123

coding=utf-8

import requests
from lxml import etree
import json

class TiebaSpider:
def init(self,tieba_name):
self.tieba_name = tieba_name
self.start_url = "http://tieba.baidu.com/mo/q----,sz@320_240-1-3---2/m?kw={}&lp=5009".format(tieba_name)
self.headers= {"User-Agent":"Mozilla/5.0 (iPhone; CPU iPhone OS 10_3 like Mac OS X) AppleWebKit/602.1.50 (KHTML, like Gecko) CriOS/56.0.2924.75 Mobile/14E5239e Safari/602.1"}
self.part_url = "http://tieba.baidu.com/mo/q----,sz@320_240-1-3---2/"

def parse_url(self,url):
    print(url)
    response = requests.get(url,headers=self.headers)
    return response.content

def get_content_list(self,html_str): #提取列表页的帖子的url，title
    html = etree.HTML(html_str)
    div_list = html.xpath("//div[contains(@class,'i')]")
    content_list = []
    for div in div_list:
        content = {}
        content["title"] = div.xpath("./a/text()")[0] if len(div.xpath("./a/text()"))>0 else None
        content["href"] = self.part_url + div.xpath("./a/@href")[0] if len( div.xpath("./a/@href"))>0 else None
        content["img_list"] = self.get_img_list(content["href"],[])  #通过函数获取图片
        content["img_list"] = [requests.utils.unquote(i.split("src=")[-1]) for i in content["img_list"]]
        content_list.append(content)
    next_url = html.xpath("//a[text()='下一页']/@href")  #获取下一页的url
    return  content_list,next_url

def get_img_list(self,detail_url,img_list):  #获取详情页的图片列表
    #3.1 请求帖子详情页
    detail_html_str = self.parse_url(detail_url)
    #3.2 提取第一页的图片
    detail_html = etree.HTML(detail_html_str)
    img_list.extend(detail_html.xpath("//img[@class='BDE_Image']/@src"))
    #3.3 获取详情页的下一页的，url
    next_url = detail_html.xpath("//a[text()='下一页']/@href")
    #3.4 循环3.1-3.3
    if len(next_url)>0:
        return self.get_img_list(self.part_url+next_url[0],img_list)
    return img_list

def save_content_list(self,content_list): #保存
    file_path = "{}_".format(self.tieba_name)
    with open(file_path,"a") as f:
        for content in content_list:
            f.write(json.dumps(content,ensure_ascii=False,indent=2))
            f.write("\n")
    print("保存成功")

def run(self): #实现主要逻辑
    next_url = [self.start_url]
    while len(next_url)>0:
        #1. start_url
        #2. 发送请求，获取响应
        next_url = next_url[0] if next_url[0].startswith("http") else self.part_url + next_url[0]
        html_str = self.parse_url(next_url)
        #3.提取列表页的帖子的url，title
        content_list,next_url = self.get_content_list(html_str)
            #3.1 请求帖子详情页
            #3.2 提取第一页的图片
            #3.3 获取详情页的下一页的，url
            #3.4 循环3.1-3.3
        #4. 保存数据
        self.save_content_list(content_list)
        #5. 提取列表页的下一页url，循环2-5

if name == 'main':
tieba_spider = TiebaSpider("123")
tieba_spider.run()

转载于:https://www.cnblogs.com/RomanticLife/p/9119716.html