單身狗福利?Python爬取某婚戀網(wǎng)征婚數(shù)據(jù)
發(fā)布日期：2022-03-22 09:54 | 文章來源：源碼中國
目標(biāo)網(wǎng)址https://www.csflhjw.com/zhenghun/34.html?page=1
一、打開界面
鼠標(biāo)右鍵打開檢查，方框里為你一個(gè)文小姐的征婚信息。。由此判斷出為同步加載
點(diǎn)擊elements，定位圖片地址，方框里為該女士的url地址及圖片地址
可以看出該女士的url地址不全，之后在代碼中要進(jìn)行url的拼接，看一下翻頁的url地址有什么變化
點(diǎn)擊第2頁
https://www.csflhjw.com/zhenghun/34.html?page=2
點(diǎn)擊第3頁
https://www.csflhjw.com/zhenghun/34.html?page=3
可以看出變化在最后
做一下fou循環(huán)格式化輸出一下。。一共10頁
二、代碼解析
1.獲取所有的女士的url，xpath的路徑就不詳細(xì)說了。。
2.構(gòu)造每一位女士的url地址
3.然后點(diǎn)開一位女士的url地址，用同樣的方法，確定也為同步加載
4.之后就是女士url地址html的xpath提取，每個(gè)都打印一下，把不要的過濾一下
5.最后就是文件的保存
打印結(jié)果：
三、完整代碼
# !/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(shù)據(jù)
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(huán)遍歷 構(gòu)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(fā)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(shù)據(jù)')):
os.mkdir(r'./{}'.format('妹子信息數(shù)據(jù)'))
csv_header = ['姓名', '學(xué)歷', '職業(yè)', '婚姻狀況', '有無子女', '是否購房', '工作地點(diǎn)', '擇偶年齡', '擇偶城市', '擇偶要求', '個(gè)人獨(dú)白', '照片鏈接']
with open(r'./{}/{}.csv'.format('妹子信息數(shù)據(jù)', '妹子數(shù)據(jù)'), '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(shù)據(jù)', '妹子數(shù)據(jù)'), '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(shù)據(jù)：{}'.format(name))
except Exception as e:
with open(r'./{}/{}.csv'.format('妹子信息數(shù)據(jù)', '妹子數(shù)據(jù)'), '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(shù)據(jù)保存成功：{}'.format(name))
if __name__ == '__main__':
main()
到此這篇關(guān)于單身狗福利？Python爬取某婚戀網(wǎng)征婚數(shù)據(jù)的文章就介紹到這了,更多相關(guān)Python爬取征婚數(shù)據(jù)內(nèi)容請搜索本站以前的文章或繼續(xù)瀏覽下面的相關(guān)文章希望大家以后多多支持本站！
版權(quán)聲明：本站文章來源標(biāo)注為YINGSOO的內(nèi)容版權(quán)均為本站所有，歡迎引用、轉(zhuǎn)載，請保持原文完整并注明來源及原文鏈接。禁止復(fù)制或仿造本網(wǎng)站，禁止在非maisonbaluchon.cn所屬的服務(wù)器上建立鏡像，否則將依法追究法律責(zé)任。本站部分內(nèi)容來源于網(wǎng)友推薦、互聯(lián)網(wǎng)收集整理而來，僅供學(xué)習(xí)參考，不代表本站立場，如有內(nèi)容涉嫌侵權(quán)，請聯(lián)系alex-e#qq.com處理。
相關(guān)文章
關(guān)注官方微信