Host: m.lianjia.com
User-Agent: Mozilla/5.0 (Windows NT 6.3; WOW64; rv:32.0) Gecko/20100101 Firefox/32.0
Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8
Accept-Language: zh-cn,zh;q=0.8,en-us;q=0.5,en;q=0.3
Accept-Encoding: gzip, deflate
Connection: keep-alive

# 获取引导频道
def getChannel(html):
    channelDict = {}
    soup = BeautifulSoup(html, "html.parser")
    channels = soup.find_all("a", attrs={"class": "inner post_ulog"})
    for channel in channels:
        list_tmp = channel.find_all("div", attrs={"class": "name"})
        channelName = list_tmp[0].get_text()
        channelHref = channel.get('href')
        channelDict[channelName] = channelHref
    return channelDict

{'海外': '/i/', '卖房': '/bj/yezhu/', '新房': '/bj/loupan/fang/', '找小区': '/bj/xiaoqu/', '查成交': '/bj/chengjiao/', '租房': '/chuzu/bj/zufang/', '二手房': '/bj/ershoufang/index/', '写字楼': 'https://shang.lianjia.com/bj/'}

# 获取城市对应的缩写
def getCity(html):
    cityDict = {}
    soup = BeautifulSoup(html, "html.parser")
    citys = soup.find_all("div", attrs={"class": "city_block"})
    for city in citys:
        list_tmp = city.find_all('a')
        for a in list_tmp:
            cityHref = a.get('href')
            cityName = a.get_text()
            cityDict[cityName] = cityHref

    return cityDict

{'文昌': '/wc/', '大理': '/dali/', '威海': '/weihai/', '达州': '/dazhou/', '中山': '/zs/', '佛山': '/fs/', '呼和浩特': '/hhht/', '合肥': '/hf/', '南昌': '/nc/', '昆明': '/km/', '定安': '/da/', '宜昌': '/yichang/', '襄阳': '/xy/', '嘉兴': '/jx/', '厦门': '/xm/', '青岛': '/qd/', '株洲': '/zhuzhou/', '西安': '/xa/', '泉州': '/quanzhou/', '济南': '/jn/', '澄迈': '/cm/', '潍坊': '/wf/', '保定': '/bd/', '绵阳': '/mianyang/', '重庆': '/cq/', '儋州': '/dz/', '南充': '/nanchong/', '南京': '/nj/', '北京': '/bj/', '杭州': '/hz/', '滁州': '/cz/', '咸宁': '/xn/', '琼海': '/qh/', '洛阳': '/luoyang/', '绍兴': '/sx/', '廊坊': '/lf/', '惠州': '/hui/', '南通': '/nt/', '上饶': '/sr/', '湛江': '/zhanjiang/', '秦皇岛': '/qhd/', '黄石': '/huangshi/', '武汉': '/wh/', '天津': '/tj/', '哈尔滨': '/hrb/', '黄冈': '/hg/', '龙岩': '/ly/', '长春': '/cc/', '珠海': '/zh/', '邢台': '/xt/', '三亚': '/san/', '北海': '/bh/', '太原': '/ty/', '德阳': '/dy/', '万宁': '/wn/', '承德': '/chengde/', '五指山': '/wzs/', '陵水': '/ls/', '成都': '/cd/', '深圳': '/sz/', '咸阳': '/xianyang/', '烟台': '/yt/', '东莞': '/dg/', '清远': '/qy/', '西双版纳': '/xsbn/', '郑州': '/zz/', '淮安': '/ha/', '漳州': '/zhangzhou/', '常德': '/changde/', '邯郸': '/hd/', '上海': '/sh/', '开封': '/kf/', '苏州': '/su/', '衡水': '/hs/', '无锡': '/wx/', '广州': '/gz/', '银川': '/yinchuan/', '徐州': '/xz/', '大连': '/dl/', '海口': '/hk/', '晋中': '/jz/', '福州': '/fz/', '新乡': '/xinxiang/', '沈阳': '/sy/', '琼中': '/qz/', '乐东': '/ld/', '淄博': '/zb/', '眉山': '/ms/', '宁波': '/nb/', '张家口': '/zjk/', '保亭': '/bt/', '长沙': '/cs/', '临高': '/lg/', '石家庄': '/sjz/', '许昌': '/xc/', '镇江': '/zj/', '乐山': '/leshan/', '贵阳': '/gy/'}

session.get(url, headers=headers)
html_set_cookie = requests.utils.dict_from_cookiejar(session.cookies)

print("构建城市编码url")
url_get_city = url_ori + "/city/"
print("获取城市编码", "：", url_get_city)
html_set_cookie, html_city = getHtml(url_get_city)
cityDict = getCity(html_city)
url_city = url_ori + cityDict[city]
print("访问获取导航", "：", url_city)
html_set_cookie, html_city_content = getHtml(url_city, _cookie=html_set_cookie)

# 解析网页
def getHtml(url, _cookie=None):
    html_bytes = session.get(url, headers=headers, cookies=_cookie)
    html_set_cookie = requests.utils.dict_from_cookiejar(session.cookies)
    return html_set_cookie, html_bytes.content.decode("utf-8", "ignore")

html_bytes = session.get(url_detail, headers=headerJson, cookies=html_set_cookie)
html_detail = html_bytes.content.decode("utf-8", "ignore")
detailJson = json.loads(html_detail)

# 获取二手房的详细信息
def getInfoErshoufang(html):
    detailArr = []

    soup = BeautifulSoup(html, "html.parser")
    detailInfo = soup.find_all("div", attrs={"class": "item_list"})
    detailUrl = soup.find_all("a", attrs={"class": "a_mask"})
    details = zip(detailInfo, detailUrl)
    for info_url in details:
        info = info_url[0]
        detailDict = {}
        # 获取标题
        title_tmp = info.find_all("div", attrs={"class": "item_main"})
        detail_title = title_tmp[0].get_text()
        # 获取房屋大小
        size_tmp = info.find_all("div", attrs={"class": "item_other"})
        detail_size = size_tmp[0].get_text()
        # 获取价格单价
        price_total_tmp = info.find_all("span", attrs={"class": "price_total"})
        detail_price_total = price_total_tmp[0].get_text()
        try:
            unit_price_tmp = info.find_all("span", attrs={"class": "unit_price"})
            detail_unit_price = unit_price_tmp[0].get_text()
        except:
            detail_unit_price = "88888888元/平"
        # 获取标签
        tag_tmp = info.find_all("div", attrs={"class": "tag_box"})
        detail_tag = tag_tmp[0].get_text()
        # 获取详情页
        url_a = info_url[1]