网络爬虫
满天星☞
加油
展开
-
链家二手房100页Xpath爬取保存csv
import randomimport timeimport csvimport requestsfrom fake_useragent import UserAgentfrom lxml import etreeclass House: def __init__(self): self.url = 'https://bj.lianjia.com/ershoufang/pg{}/' self.f = open('链家100.csv','w')原创 2021-06-27 14:37:22 · 403 阅读 · 0 评论 -
python爬虫爬取网站小说
#加载模块import requestsfrom bs4 import BeautifulSoup# 定义所有章节和链接函数def get_novel_chapters(): url = "https://www.89wxw.com/read/1037/" r = requests.get(url) main_page = BeautifulSoup(r.text, "html.parser") list1 = [] for dd in (main_page原创 2021-04-04 13:00:03 · 278 阅读 · 0 评论