0
点赞
收藏
分享

微信扫一扫

amazon爬虫代码简单易改

十里一走马 2022-01-13 阅读 88

amazon爬虫代码

def amazon(url):
    driver.get(url)
    time.sleep(2)
    title=driver.find_element_by_xpath("//*[@id='cm_cr-product_info']").find_element_by_tag_name("h1").get_attribute("textContent").replace("\n","")
    time.sleep(2)
    author=driver.find_element_by_xpath("//*[@id='cr-arp-byline']").find_element_by_tag_name("a").get_attribute("textContent").replace("\n","")
    time.sleep(2)
    comment_text=title+','+author

    start_flag = True
    while True:
        reviews=driver.find_element_by_xpath("//*[@id='cm_cr-review_list']").find_elements_by_css_selector(".a-section.review.aok-relative")
        time.sleep(2)
        for review in reviews:
            name=review.find_element_by_tag_name("span").get_attribute("textContent").replace("\n","").replace(",",".")
            time.sleep(2)
            score=review.find_element_by_class_name("a-icon-alt").get_attribute("textContent")[0:6]
            time.sleep(2)
            comment=review.find_element_by_css_selector(".a-size-base.review-text.review-text-content").get_attribute("textContent").replace("\n","").replace(",",".").strip()
            time.sleep(2)
            comment_text=comment_text+'\n'+name+','+score+','+comment
        try: 
            next_page=driver.find_element_by_class_name("a-last").find_element_by_tag_name("a").get_attribute("href")
            time.sleep(2)
            driver.get(next_page)
            time.sleep(2)
        except:
            break

    with open('/Users/jiajiazhou/Downloads/comments_amazon.csv','a',encoding="utf-8_sig") as f:
        f.write('\n')
        f.write('\n')
        f.write(comment_text)
        f.close()
举报

相关推荐

0 条评论