python爬取百度谷歌搜索结果

使用requests模块爬取百度或者谷歌搜索结果，，如下代码示例是百度的，修改为谷歌的话研究下谷歌url的格式替换下即可，
把要搜索的字段写入一个文件中，每行写一个，运行的第一个参数为文件路径，按代码中的保存格式将结果保存在当前目录的文件中；
代码如下

# coding=utf-8

import os
import random
import sys
import time
import json
import logging
import datetime
import requests


logging.basicConfig(level=logging.DEBUG,
                    format='%(asctime)s - %(levelname)s - %(message)s')

USER_AGENT = ['Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20130406 Firefox/23.0',
               'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:18.0) Gecko/20100101 Firefox/18.0',
               'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/533+ \
               (KHTML, like Gecko) Element Browser 5.0',
               'IBM WebExplorer /v0.94', 'Galaxy/1.0 [en] (Mac OS X 10.5.6; U; en)',
               'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0)',
               'Opera/9.80 (Windows NT 6.0) Presto/2.12.388 Version/12.14',
               'Mozilla/5.0 (iPad; CPU OS 6_0 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko) \
               Version/6.0 Mobile/10A5355d Safari/8536.25',
               'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) \
               Chrome/28.0.1468.0 Safari/537.36',
               'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.0; Trident/5.0; TheWorld)']


class GoogleSpider:

    def __init__(self, query_file):

        self.query_file = query_file
        self.temp_url = "https://www.baidu.com/s?wd={}"
        self.query_list = []
        self.url_list = []
        user_agent = random.choice(USER_AGENT)
        self.headers = {
            "User-Agent": user_agent}
        self.save_list = []

    def get_query(self):
        """
        从文件中查找要搜索的字段
        :return:
        """

        if not os.path.exists(self.query_file):
            logging.error("请检查文件名路径")

        with open(self.query_file, "r", encoding="utf-8") as file:
            for word in file:
                self.query_list.append(word.strip())

    def get_url_list(self):
        """
        获取所有要搜索的url
        :return:
        """

        self.url_list = [self.temp_url.format(query) for query in self.query_list]

    def parse_url(self):
        """
        解析每一个url，每个请求停顿一秒，防止被识别为爬虫
        :return:
        """

        for url in self.url_list:
            word = self.query_list[self.url_list.index(url)]

            response = requests.get(url, headers=self.headers)

            if response.status_code != 200:
                logging.error("{}搜索请求失败".format(word))

            save_format = dict()
            save_format["query"] = word
            save_format["html"] = response.content.decode()
            save_format["datatime"] = datetime.datetime.now().strftime('%Y%m%d')

            self.save_list.append(save_format)
            time.sleep(1)

    def write_to_file(self):
        """
        将读取的内容按照特定格式保存至文件中
        :return:
        """

        with open("success_query.txt", "w", encoding="utf-8") as file:
            for content in self.save_list:
                file.write(str(content))
                file.write("\n")

        logging.info("请在当前目录下查看success_query.txt")

    def run(self):

        # 从query文件中读取要查询的字段
        self.get_query()

        # 获取url列表
        self.get_url_list()

        # 发送请求获取数据
        self.parse_url()

        # 将数据写入文件中
        self.write_to_file()


if __name__ == '__main__':
    try:
        query = sys.argv[1]
        google = GoogleSpider(query)
        google.run()

    except IndexError:
        logging.error("未找到查找目录")

    except Exception as e:

        logging.error(e)