[Python知识库]2021-09-03 爬虫模板（只支持静态页面）

# -*- coding: utf-8 -*-
# @Time    : 2021/9/3 21:32
# @Author  : Yj Xue
# @FileName: entity_car.py
# @Software: PyCharm 2020.2.2 x64
# @Blog    ：https://blog.csdn.net/qq_37150711/category_9396602.html

from requests_html import HTMLSession
from requests_html import HTML
import requests
import time
import json
import random
import sys
import os
import csv

from fake_useragent import UserAgent

session = HTMLSession()
url = 'https://car.autohome.com.cn/price/series-4392.html'
#https://car.autohome.com.cn/config/series/3862.html

USER_AGENTS = [
    "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_7_3) AppleWebKit/535.20 (KHTML, like Gecko) Chrome/19.0.1036.7 Safari/535.20",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/535.11 (KHTML, like Gecko) Chrome/17.0.963.84 Safari/535.11 LBBROWSER",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E)",
    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
    "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 5.1; Trident/4.0; SV1; QQDownload 732; .NET4.0C; .NET4.0E; 360SE)",
    "Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; QQDownload 732; .NET4.0C; .NET4.0E)",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.89 Safari/537.1",
    "Mozilla/5.0 (iPad; U; CPU OS 4_2_1 like Mac OS X; zh-cn) AppleWebKit/533.17.9 (KHTML, like Gecko) Version/5.0.2 Mobile/8C148 Safari/6533.18.5",
    "Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:2.0b13pre) Gecko/20110307 Firefox/4.0b13pre",
    "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:16.0) Gecko/20100101 Firefox/16.0",
    "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11",
    "Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10"
]

#写入CSV文件
def save2csv(writer,bank):
        header = ['bank','num' 'url']
        #writer.writerow(header)
        csvrow1 = []
        csvrow1.append(bank)

        writer.writerow(csvrow1)


headers = {"User-Agent": random.choice(USER_AGENTS)} # 这里是一个关键的反爬虫策略！
session = HTMLSession()

# 逐个URL进行爬取
response = session.get(url, headers=headers)
response.html.render() # 反爬虫技术（模拟人机交互）
print(response)
response.encoding = 'gb2312'
print(response.text)
print("URL=", url)

banks = response.html.find('.interval01-list-cars div p a') # 这是网页上的路径

print(banks)

current_dir = os.path.abspath('.')
file_name = os.path.join(current_dir, "data\\entity.csv")

# bank = banks[0]
# bank.default_decoding = 'utf-8'
# print(type(bank.text))
# bank = bank.text.encode('utf-8')
# print(bank)
# exit(0)

with open(file_name, 'wt', newline='', encoding='gb2312')  as csvfile1:
    for bank in banks:
        print(bank.text)
        writer = csv.writer(csvfile1)  # 构建好这个对象很重要！
        # 返回的是列表
        bk = bank.text # 获取品牌的内容
        # 逆序查找：车系
        print(bk)
        save2csv(writer, bk)
        csvfile1.flush()

print('over!')