Python——爬取瓜子二手车

# coding:utf8
# author:Jery
# datetime:2019/5/1 5:16
# software:PyCharm
# function:爬取瓜子二手车
import requests
from lxml import etree
import re
import csv

start_url = 'https://www.guazi.com/www/buy/o1c-1'
headers = {
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.103 Safari/537.36',
    'Cookie': 'uuid=6032a689-d79a-4060-c8b0-f57d8db4e245; antipas=16I7A500578955101K231sG39E; clueSourceCode=10103000312%2300; user_city_id=49; ganji_uuid=3434204287155953305008; sessionid=405f3fb6-fb90-409d-c7ed-32874a157920; lg=1; cainfo=%7B%22ca_s%22%3A%22pz_baidu%22%2C%22ca_n%22%3A%22tbmkbturl%22%2C%22ca_medium%22%3A%22-%22%2C%22ca_term%22%3A%22-%22%2C%22ca_content%22%3A%22%22%2C%22ca_campaign%22%3A%22%22%2C%22ca_kw%22%3A%22-%22%2C%22keyword%22%3A%22-%22%2C%22ca_keywordid%22%3A%22-%22%2C%22scode%22%3A%2210103000312%22%2C%22ca_transid%22%3A%22%22%2C%22platform%22%3A%221%22%2C%22version%22%3A1%2C%22ca_i%22%3A%22-%22%2C%22ca_b%22%3A%22-%22%2C%22ca_a%22%3A%22-%22%2C%22display_finance_flag%22%3A%22-%22%2C%22client_ab%22%3A%22-%22%2C%22guid%22%3A%226032a689-d79a-4060-c8b0-f57d8db4e245%22%2C%22sessionid%22%3A%22405f3fb6-fb90-409d-c7ed-32874a157920%22%7D; cityDomain=mianyang; _gl_tracker=%7B%22ca_source%22%3A%22-%22%2C%22ca_name%22%3A%22-%22%2C%22ca_kw%22%3A%22-%22%2C%22ca_id%22%3A%22-%22%2C%22ca_s%22%3A%22self%22%2C%22ca_n%22%3A%22-%22%2C%22ca_i%22%3A%22-%22%2C%22sid%22%3A20570070983%7D; preTime=%7B%22last%22%3A1556660763%2C%22this%22%3A1556659891%2C%22pre%22%3A1556659891%7D'
}


# 获取详情页面url
def get_detail_urls(url):
    response = requests.get(url, headers=headers)
    text = response.content.decode('utf-8')
    html = etree.HTML(text)
    index = html.xpath('//ul[@class="pageLink clearfix"]/li[@class="link-on"]/a/span/text()')
    next_url = html.xpath('//ul[@class="pageLink clearfix"]/li/a/@href')[-1]
    ul = html.xpath('//ul[@class="carlist clearfix js-top"]')[0]
    lis = ul.xpath('./li')
    urls = []
    for li in lis:
        detail_url = li.xpath('./a/@href')
        detail_url = 'https://www.guazi.com' + detail_url[0]
        urls.append(detail_url)
    return urls, index, next_url


def get_info(url):
    response = requests.get(url, headers=headers)
    text = response.content.decode('utf-8')
    html = etree.HTML(text)
    infos_dict = {}
    city = html.xpath('//p[@class="city-curr"]/text()')[0]
    city = re.search(r'[u4e00-u9fa5]+', city).group(0)
    infos_dict['city'] = city
    title = html.xpath('//div[@class="product-textbox"]/h2/text()')[0]
    infos_dict['title'] = title.replace(r'
', '').strip()
    infos = html.xpath('//div[@class="product-textbox"]/ul/li/span/text()')
    infos_dict['cardtime'] = infos[0]
    infos_dict['kms'] = infos[1]
    if len(infos) == 4:
        infos_dict['cardplace'] = ''
        infos_dict['displacement'] = infos[2]
        infos_dict['speedbox'] = infos[3]
    else:
        infos_dict['cardplace'] = infos[2]
        infos_dict['displacement'] = infos[3]
        infos_dict['speedbox'] = infos[4]

    price = html.xpath('//div[@class="product-textbox"]/div/span[@class="pricestype"]/text()')[0]
    infos_dict['price'] = re.search(r'd+.?d+', price).group(0)
    return infos_dict


def main():
    with open(r"C:UsersJeryDesktopguazi.csv", 'w', newline='') as f:
        csvwriter_head = csv.writer(f, dialect='excel')
        csvwriter_head.writerow(['城市', '车型', '上牌时间', '上牌地', '表显里程', '排量', '变速箱', '价格'])
    while True:
        global start_url
        urls, index, next_url = get_detail_urls(start_url)
        print("当前页码：{}*****************".format(index))
        # 写表头
        with open(r'C:UsersJeryDesktopguazi.csv', 'a') as f:
            for url in urls:
                print("正在爬取：{}".format(url))
                infos = get_info(url)
                print(infos)
                csvwriter = csv.writer(f, dialect='excel')
                csvwriter.writerow(
                    [infos['city'], infos['title'], infos['cardtime'], infos['cardplace'], infos['kms'],
                     infos['displacement'],
                     infos['speedbox'],
                     infos['price']])
        if next_url:
            start_url = 'https://www.guazi.com' + next_url


if __name__ == '__main__':
    main()

后续将进行数据分析