使用selenium获取百度搜索内容_selenium爬取百度搜索结果

from selenium import webdriver
import csv
import threading
import time
from lxml import etree
from queue import Queue


class BaiduSpider(object):
    def __init__(self):
        self.url = 'https://www.baidu.com/'
        self.driver = webdriver.Chrome()
        self.q = Queue()

    def get_first_page(self):
        self.driver.get(self.url)
        self.driver.find_element_by_name('wd').send_keys('注册页面')
        self.driver.find_element_by_id('su').click()
        time.sleep(2)

    def parse_page(self):
        response = self.driver.page_source
        html = etree.HTML(response)
        hrefs = html.xpath('//div[@class="result c-container "]/h3[@class="t"]/a/@href')
        flag = html.xpath('//div[@id="page"]/a[last()]/@class')[0]
        return flag, hrefs

    def parse_detail_page(self):
        while True:
            if self.q.qsize():
                # 获取队列中的URL
                url = self.q.get()
                driver = webdriver.Chrome()
                driver.get(url)
                try:
                    html = driver.page_source
                except:
                    driver.quit()
                else:
                    driver.quit()
                    # 保存到本地
                    self.save_new_url(url)
            else:
                time.sleep(10)

    def get_page_html(self):
        # 获取第一页数据
        self.get_first_page()
        page_num = 1
        while True:
            # 解析页面数据，判定是否继续爬取，以及获取详情页的URL
            flag, urls = self.parse_page()
            # 判断是否为末页
            if flag != 'n':
                print('已爬取百度全部数据')
                break
            # 将详情页URL加入队列
            for url in urls:
                self.q.put(url)
            # 跳转至下一页
            time.sleep(4)
            self.driver.find_element_by_xpath('//div[@id="page"]/a[last()]').click()

    def get_dtail_html(self):
        while True:
            if self.q.qsize() != 0:
                print(self.q.qsize())
                url = self.q.get()
                print(url)
            else:
                time.sleep(5)

    def run(self):
        # 获取每页URL
        c = threading.Thread(target=self.get_page_html)
        c.start()
        # 解析详情页
        t = threading.Thread(target=self.get_dtail_html)
        t.start()


if __name__ == '__main__':
    zhuce = BaiduSpider()
    zhuce.run()
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84