單身狗福利?Python爬取某婚戀網征婚數據

# !/usr/bin/nev python
# -*-coding:utf8-*-

import requests, os, csv
from pprint import pprint
from lxml import etree

def main():
    for i in range(1, 11):
        start_url = 'https://www.csflhjw.com/zhenghun/34.html?page={}'.format(i)

        headers = {
            'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) '
                          'Chrome/87.0.4280.88 Safari/537.36'

        }
        response = requests.get(start_url, headers=headers).content.decode()
        # # pprint(response)
        # 3 解析數據
        html_str = etree.HTML(response)
        info_urls = html_str.xpath(r'//div[@class="e"]/div[@class="e-img"]/a/@href')
        # pprint(info_urls)

        # 4、循環遍歷 構造img_info_url
        for info_url in info_urls:
            info_url = r'https://www.csflhjw.com' + info_url
            # print(info_url)
            # 5、對info_url發請求，解析得到img_urls
            response = requests.get(info_url, headers=headers).content.decode()
            html_str = etree.HTML(response)
            # pprint(html_str)
            img_url = 'https://www.csflhjw.com/' + html_str.xpath(r'/html/body/div[4]/div/div[1]/div[2]/div[1]/div['
                                                                r'1]/img/@src')[0]
            # pprint(img_url)
            name = html_str.xpath(r'//div[@class="team-info"]/div[@class="team-e"]/h2/text()')[0]
            # pprint(name)
            xueli = html_str.xpath(r'//div[@class="team-info"]/div[@class="team-e"]/p[1]/text()')[0].split('：')[1]
            # pprint(xueli)
            job = html_str.xpath(r'//div[@class="team-info"]/div[@class="team-e"]/p[2]/text()')[0].split('：')[1]
            # pprint(job)
            marital_status = html_str.xpath(r'//div[@class="team-info"]/div[@class="team-e"]/p[3]/text()')[0].split(
                '：')[1]
            # pprint(marital_status)
            is_child = html_str.xpath(r'//div[@class="team-info"]/div[@class="team-e"]/p[4]/text()')[0].split('：')[1]
            # pprint(is_child)
            home = html_str.xpath(r'//div[@class="team-info"]/div[@class="team-e"]/p[5]/text()')[0].split('：')[1]
            # pprint(home)
            workplace = html_str.xpath(r'//div[@class="team-info"]/div[@class="team-e"]/p[6]/text()')[0].split('：')[1]
            # pprint(workplace)
            requ = html_str.xpath(r'/html/body/div[4]/div/div[1]/div[2]/div[2]/div[2]/p[2]/span/text()')[0].split('：')[1]
            # pprint(requ)
            requ = [requ if requ != str() else '無要求'][0]
            monologue = html_str.xpath(r'//div[@class="hunyin-1-3"]/p/text()')
            # pprint(monologue)
            monologue = [monologue[0].replace(' ', '').replace('\xa0', '') if monologue !=list() else '無'][0]
            # pprint(monologue)
            zeo_age = html_str.xpath(r'/html/body/div[4]/div/div[1]/div[2]/div[2]/div[2]/p[1]/span[1]/text()')[0].split('：')[1]
            zeo_age = [zeo_age if zeo_age!=str() else '無要求'][0]
            # pprint(zeo_age)
            zeo_address = html_str.xpath(r'/html/body/div[4]/div/div[1]/div[2]/div[2]/div[2]/p[1]/span[2]/text()')[0].split('：')[1]
            zeo_address = [zeo_address if zeo_address!=str() else '無要求'][0]
            # pprint(zeo_address)

            if not os.path.exists(r'./{}'.format('妹子信息數據')):
                os.mkdir(r'./{}'.format('妹子信息數據'))
                csv_header = ['姓名', '學歷', '職業', '婚姻狀況', '有無子女', '是否購房', '工作地點', '擇偶年齡', '擇偶城市', '擇偶要求', '個人獨白', '照片鏈接']
                with open(r'./{}/{}.csv'.format('妹子信息數據', '妹子數據'), 'w', newline='', encoding='gbk') as file_csv:
                    csv_writer_header = csv.DictWriter(file_csv, csv_header)
                    csv_writer_header.writeheader()

            try:
                with open(r'./{}/{}.csv'.format('妹子信息數據', '妹子數據'), 'a+', newline='',
                          encoding='gbk') as file_csv:
                    csv_writer = csv.writer(file_csv, delimiter=',')
                    csv_writer.writerow([name, xueli, job, marital_status, is_child, home, workplace, zeo_age,
                                         zeo_address, requ, monologue, img_url])
                    print(r'***妹子信息數據：{}'.format(name))
            except Exception as e:
                with open(r'./{}/{}.csv'.format('妹子信息數據', '妹子數據'), 'a+', newline='',
                          encoding='utf-8') as file_csv:
                    csv_writer = csv.writer(file_csv, delimiter=',')
                    csv_writer.writerow([name, xueli, job, marital_status, is_child, home, workplace, zeo_age,
                                         zeo_address, requ, monologue, img_url])
                    print(r'***妹子信息數據保存成功：{}'.format(name))



if __name__ == '__main__':
    main()