用Python和selenium刮URL

Question

>

取文本文件booktitle.txt，它是书名列表。

然后使用Python/Selenium在网站goodreads.com中搜索该标题。

获取结果的URL并创建一个新的.csv文件，其中列1=书名，列2=站点URL

from selenium import webdriver
from selenium.webdriver.support.ui import WebDriverWait
from selenium.webdriver.support import expected_conditions as EC
from selenium.webdriver.common.by import By
from selenium.common.exceptions import TimeoutException
from selenium.webdriver.firefox.options import Options
from pyvirtualdisplay import Display
#from selenium.webdriver.chrome.options import Options
from selenium.webdriver.support.ui import Select
from selenium.webdriver.common import keys
import csv
import time
import json

class Book:
    def __init__(self, title, url):
        self.title = title
        self.url = url
    def __iter__(self):
        return iter([self.title, self.url])

url = 'https://www.goodreads.com/'

def create_csv_file():
    header = ['Title', 'URL']
    with open('/home/l/gDrive/AudioBookReviews/WebScraping/GoodReadsBooksNew.csv', 'w+', encoding='utf-8') as csv_file:
        wr = csv.writer(csv_file, delimiter=',')
        wr.writerow(header)

def read_from_txt_file():
    lines = [line.rstrip('\n') for line in open('/home/l/gDrive/AudioBookReviews/WebScraping/BookTitles.txt', encoding='utf-8')]
    return lines

def init_selenium():
    chrome_options = Options()
    chrome_options.add_argument('--no-sandbox')
    chrome_options.add_argument('--disable-dev-shm-usage') 
    options = Options()
    options.add_argument('--headless')
    global driver
    driver = webdriver.Chrome("/home/l/gDrive/AudioBookReviews/WebScraping/chromedriver",  chrome_options=chrome_options)
    driver.get(url)
    time.sleep(30)
    driver.get('https://www.goodreads.com/search?q=')

def search_for_title(title):
    search_field = driver.find_element_by_xpath('//*[@id="search_query_main"]')
    search_field.clear()
    search_field.send_keys(title)
    search_button = driver.find_element_by_xpath('/html/body/div[2]/div[3]/div[1]/div[1]/div[2]/form/div[1]/input[3]')
    search_button.click()

def scrape_url():
    try:
        url = driver.find_element_by_css_selector('a.bookTitle').get_attribute('href')
    except:
        url = "N/A"

    return url

def write_into_csv_file(vendor):
   with open('/home/l/gDrive/AudioBookReviews/WebScraping/GoodReadsBooksNew.csv', 'a', encoding='utf-8') as csv_file:
        wr = csv.writer(csv_file, delimiter=',')
        wr.writerow(list(vendor))

create_csv_file()
titles = read_from_txt_file()    
init_selenium()

for title in titles:
    search_for_title(title)
    url = scrape_url()
    book = Book(title, url)
    write_into_csv_file(book)

Answer 1

现在我能看到几个错误：

1）当您稍后在代码中传递chromedriver时，您必须取消注释chrome选项并注释Firefox

# from selenium.webdriver.firefox.options import Options
from selenium.webdriver.chrome.options import Options

顺便说一句，pyvirtualdisplay是无头chrome替代品，您不需要导入它。

def init_selenium():
    chrome_options = Options()
    chrome_options.add_argument('--no-sandbox')
    chrome_options.add_argument('--disable-dev-shm-usage') 
    chrome_options.add_argument('--headless')