豆瓣小组爬虫

最近要租房，写了一个豆瓣租房小组的爬虫，直接上代码
python 复制代码
from lxml import etree
import requests
import time  
import pandas as pd
import tqdm

def get_code(start, group_url):
    url = group_url
    headers = {
   #填自己登录之后的cookie 参考教程https://blog.csdn.net/weixin_41666747/article/details/80315002
    }
    data = {
    'start': start,
    'type': 'new'
    }
    request = requests.get(url=url, params=data, headers=headers)
    response = request.text
    return response


def list_posts(response, page, titles, urls, dates, authors, replies):
    tree = etree.HTML(response)
    titles_arr = tree.xpath('//table[@class="olt"]/tr//td/a/@title')
    for t in range(len(titles_arr)):
        titles[page].append(titles_arr[t])
    urls_arr = tree.xpath('//table[@class="olt"]/tr//td[@class="title"]//a/@href')
    for u in range(len(urls_arr)):
        urls[page].append(urls_arr[u])
    dates_arr = tree.xpath('//table[@class="olt"]/tr//td[@class="time"]/text()')
    for d in range(len(dates_arr)):
        dates[page].append(dates_arr[d])
    authors_arr = tree.xpath('//table[@class="olt"]/tr//td[@nowrap="nowrap"]/a/text()')
    for a in range(len(authors_arr)):
        authors[page].append(authors_arr[a])
    replies_arr = tree.xpath('//table[@class="olt"]/tr//td[@class="r-count "]/text()')
    for r in range(len(replies_arr)):
        replies[page].append(replies_arr[r])
    return titles, urls, dates, authors, replies


def get_page(all_page, group_url):
    titles = [[] for i in range(all_page)]
    urls = [[] for i in range(all_page)]
    dates = [[] for i in range(all_page)]
    authors = [[] for i in range(all_page)]
    replies = [[] for i in range(all_page)]
    for i in tqdm.tqdm(range(all_page)):
        start = i * 25
        time.sleep(0.05)
        response = get_code(start, group_url)
        titles, urls, dates, authors, replies = list_posts(response, i, titles, urls, dates, authors, replies)
    return titles, urls, dates, authors, replies


#北京租房 100万+ 个成员 在此聚集
group_url = 'https://www.douban.com/group/beijingzufang/discussion'
# 北京租房 481519 个成员 在此聚集
group_url = 'https://www.douban.com/group/sweethome/discussion'

all_page = 100
print('正在爬取' + str(int(all_page) * 25) + '篇帖子，请稍后...')

titles, urls, dates, authors, replies = get_page(int(all_page), group_url)

data = []  

for i in range(int(all_page)):
    for j in range(len(titles[i])):
        data.append({"Title": titles[i][j], "Author": authors[i][j], "Date": dates[i][j], "Url": urls[i][j]})  
#             print("【查找成功！第%d页】" % (i + 1))
#             print("标题：" + titles[i][j])
#             print("作者：" + authors[i][j])
# #             print("回复数：" + replies[i][j])
#             print("最后回复时间：" + dates[i][j])
#             print("链接：" + urls[i][j])
#             print('-----------------------------------------------------')
df = pd.DataFrame(data)  
# 将表格写入Excel文件  
df.to_excel("output.xlsx", index=True)
print('爬取完成！')