时间:2020-07-08 python爬虫 查看: 1000
爬取某人的微博数据,把某人所有时间段的微博数据都爬下来。
具体思路:
创建driver-----get网页----找到并提取信息-----保存csv----翻页----get网页(开始循环)----...----没有“下一页”就结束,
用了while True,没用自我调用函数
嘟大海的微博:https://weibo.com/u/1623915527
办公室小野的微博:https://weibo.com/bgsxy
代码如下
from selenium import webdriver
from selenium.webdriver.common.keys import Keys
import csv
import os
import time
#只有这2个参数设置,想爬谁的微博数据就在这里改地址和目标csv名称就行
weibo_url = 'https://weibo.com/bgsxy?profile_ftype=1&is_all=1#_0'
csv_name = 'bgsxy_allweibo.csv'
def start_chrome():
print('开始创建浏览器')
driver = webdriver.Chrome(executable_path='C:/Users/lori/Desktop/python52project/chromedriver_win32/chromedriver.exe')
driver.start_client()
return driver
def get_web(url): #获取网页,并下拉到最底部
print('开始打开指定网页')
driver.get(url)
time.sleep(7)
scoll_down()
time.sleep(5)
def scoll_down(): # 滚轮下拉到最底部
html_page = driver.find_element_by_tag_name('html')
for i in range(7):
print(i)
html_page.send_keys(Keys.END)
time.sleep(1)
def get_data():
print('开始查找并提取数据')
card_sel = 'div.WB_cardwrap.WB_feed_type'
time_sel = 'a.S_txt2[node-type="feed_list_item_date"]'
source_sel = 'a.S_txt2[suda-uatrack="key=profile_feed&value=pubfrom_guest"]'
content_sel = 'div.WB_text.W_f14'
interact_sel = 'span.line.S_line1>span>em:nth-child(2)'
cards = driver.find_elements_by_css_selector(card_sel)
info_list = []
for card in cards:
time = card.find_elements_by_css_selector(time_sel)[0].text #虽然有可能在一个card中有2个time元素,我们取第一个就对
if card.find_elements_by_css_selector(source_sel):
source = card.find_elements_by_css_selector(source_sel)[0].text
else:
source = ''
content = card.find_elements_by_css_selector(content_sel)[0].text
link = card.find_elements_by_css_selector(time_sel)[0].get_attribute('href')
trans = card.find_elements_by_css_selector(interact_sel)[1].text
comment = card.find_elements_by_css_selector(interact_sel)[2].text
like = card.find_elements_by_css_selector(interact_sel)[3].text
info_list.append([time,source,content,link,trans,comment,like])
return info_list
def save_csv(info_list,csv_name):
csv_path = './' + csv_name
print('开始写入csv文件')
if os.path.exists(csv_path):
with open(csv_path,'a',newline='',encoding='utf-8-sig') as f: #newline=''避免空行;encoding='utf-8-sig'比utf8牛,保存中文没问题
writer = csv.writer(f)
writer.writerows(info_list)
else:
with open(csv_path,'w+',newline='',encoding='utf-8-sig') as f:
writer = csv.writer(f)
writer.writerow(['发布时间','来源','内容','链接','转发数','评论数','点赞数'])
writer.writerows(info_list)
time.sleep(5)
def next_page_url():
next_page_sel = 'a.page.next'
next_page_ele = driver.find_elements_by_css_selector(next_page_sel)
if next_page_ele:
return next_page_ele[0].get_attribute('href')
else:
return None
driver = start_chrome()
input('请在chrome中登录weibo.com') # 暂停程序,手动登录weibo.com
while True:
get_web(weibo_url)
info_list = get_data()
save_csv(info_list,csv_name)
if next_page_url():
weibo_url = next_page_url()
else:
print('爬取结束')
break
以上就是本文的全部内容,希望对大家的学习有所帮助,也希望大家多多支持python博客。