多线程爬虫链家基本信息

一、代码

这里没有什么反爬措施，所以就不分析了，直接上代码
import hashlib
import re
from concurrent.futures import ThreadPoolExecutor
from urllib import parse
import requests
from bs4 import BeautifulSoup
from pymongo import MongoClient

session = requests.session()

# 创建线程池
pool = ThreadPoolExecutor(10)

# Mongo链接
client = MongoClient('mongodb://10.0.0.101:27017/')
db = client['db1']
lianjia = db['lianjia']

headers = {
    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/88.0.4324.150 Safari/537.36"
}

# 解析存储
def parse_page(html):
    if hasattr(html, "_Future__get_result"):
        html = html.result()
    soup = BeautifulSoup(html, "lxml")
    li_list = soup.find("ul", attrs={"class": "sellListContent"}).find_all("li", attrs={
        "class": "clear LOGVIEWDATA LOGCLICKDATA"}, recursive=False)
    for li in li_list:
        title = li.find("div", attrs={"class": "title"})
        flood = li.find("div", attrs={"class": "flood"})
        address = li.find("div", attrs={"class": "address"})
        followInfo = li.find("div", attrs={"class": "followInfo"})
        tag = li.find("div", attrs={"class": "tag"})
        priceInfo = li.find("div", attrs={"class": "priceInfo"})
        # print(title.text)
        # print(flood.text)
        # print(address.text)
        # print(followInfo.text)
        # print(tag.text)
        # print(priceInfo.text)
        # 将标题进行MD5转换作为id
        md = hashlib.md5()
        md.update(title.text.encode("utf-8"))
        id = md.hexdigest()
        if not lianjia.find_one({"_id": id}):
            lianjia.insert({"_id": id, "title": title.text, "flood": flood.text, "address": address.text,
                            "followInfo": followInfo.text, "tag": tag.text,"priceInfo":priceInfo.text})

# 首页内容
def first_page(search_key):
    res = session.get(url="https://sh.lianjia.com/ershoufang/rs%s" % (search_key))
    soup = BeautifulSoup(res.text, "lxml")
    # 获取房子总数用来判断分页数量
    total_num = int(re.search("[0-9]d*", soup.find("h2", attrs={"class": "total fl"}).text).group())
    return res.text, total_num

# 分页内容
def range_page(num, search_key):
    res = session.get(url="https://sh.lianjia.com/ershoufang/pg%srs%s" % (num, search_key))
    return res.text


def run(search_key, total_num=None):
    search_key = parse.quote(search_key)
    if not total_num:
        html, total_num = first_page(search_key)
        parse_page(html)
        for num in range(2, (total_num // 30)+1): # 每页有30条数据，区余后获取分页总数
            pool.submit(range_page, num, search_key).add_done_callback(parse_page)
    else:
        html, _ = first_page(search_key)
        parse_page(html)
        for num in range(2, total_num):
            pool.submit(range_page, num, search_key).add_done_callback(parse_page)

run("浦东")
多线程爬虫链家基本信息

一、代码

二、结果
