簡(jiǎn)述

爬取所有的中大微博的信息。包括文本文件和視頻文件，亦或是是圖片文件。

代碼實(shí)現(xiàn)

from gevent import monkey import geventmonkey.patch_all(select=False) import selenium from selenium import webdriver import time from selenium.webdriver.common.by import By from selenium.webdriver.support.ui import WebDriverWait from selenium.webdriver.support import expected_conditions as EC import os import shutil import requestsdef scroll():try:browser.find_element_by_xpath('//div[@class="W_pages"]')except:return Falsereturn Truedef checkfile(filepath):if os.path.exists(filepath):shutil.rmtree(filepath)os.mkdir(filepath)def writeText(text, filepath):with open(os.path.join(filepath, 'text.txt'), 'w', encoding='utf-8', errors='ignore') as f:f.write(text)def writeMedia(mediaurl, filepath, name, vedio=False):if not vedio:form = os.path.splitext(mediaurl)[-1]else:form = '.mp4'with open(os.path.join(filepath, name + form), 'wb') as f:f.write(requests.get(mediaurl).content)if __name__ == '__main__':options = webdriver.ChromeOptions()options.binary_location = r"D:\Software\Chrome\Application\chrome.exe"browser = webdriver.Chrome(chrome_options=options)url = 'https://weibo.com/u/1892723783?is_all=1'browser.get(url)time.sleep(40)WB_innerwrap = browser.find_element_by_css_selector('div[class="WB_innerwrap"]')# 總共的數(shù)量td_last_number = int(WB_innerwrap.find_elements_by_tag_name('td')[-1].find_element_by_class_name("W_f16").text)print("微博總數(shù):", td_last_number)file_path = './weibo'checkfile(file_path)medialist = []MAXLEN = 50for TIMES in range(221):while not scroll():browser.execute_script("window.scrollBy(0,10000)")time.sleep(5)WB_feed = browser.find_element_by_css_selector('div[module-type="feed"]')feed_content = WB_feed.find_elements_by_xpath('//div[@node-type="feed_content"]')for feed_list_item in feed_content:print("#### BEGIN", td_last_number)WB_detail = feed_list_item.find_element_by_class_name('WB_detail')WB_text = WB_detail.find_element_by_css_selector('div[node-type="feed_list_content"]').text# 創(chuàng)建文件夾feed_list_item_file_path = os.path.join(file_path, str(td_last_number))checkfile(feed_list_item_file_path)writeText(WB_text, feed_list_item_file_path)td_last_number -= 1try:WB_media_box = WB_detail.find_element_by_class_name('media_box')imgs = WB_media_box.find_elements_by_tag_name('img')for i, img in enumerate(imgs):# print('image ', i, img.get_attribute('src'))medialist.append(gevent.spawn(writeMedia, img.get_attribute('src'), feed_list_item_file_path,'image ' + str(i)))videos = WB_media_box.find_elements_by_tag_name('video')for video in videos:# print('video', video.get_attribute('src'))medialist.append(gevent.spawn(writeMedia, video.get_attribute('src'), feed_list_item_file_path,'veido', True))except:passif len(medialist) >= MAXLEN:gevent.joinall(medialist)medialist = []W_pages = browser.find_element_by_xpath('//div[@class="W_pages"]')W_pages.find_elements_by_tag_name('a')[-1].click()if len(medialist):gevent.joinall(medialist)medialist = []else:time.sleep(5)

總結(jié)

以上是生活随笔為你收集整理的爬取某一微博用户所有文本文件或者是视频图片文件的全部?jī)?nèi)容，希望文章能夠幫你解決所遇到的問題。

如果覺得生活随笔網(wǎng)站內(nèi)容還不錯(cuò)，歡迎將生活随笔推薦給好友。