Question

我正在尝试遍历多个页面，而我的代码不会提取任何内容。我有点新手去抓我跟熊一样。我做了一个容器，所以我可以针对每个列表。我还制作了一个变量来定位您要按下的锚标记转到下一页。我真的很感激我能得到的任何帮助。感谢。

from urllib.request import urlopen as uReq
from bs4 import BeautifulSoup as soup

for page in range(0,25):
    file = "breakfeast_chicago.csv"
    f = open(file, "w")
    Headers = "Nambusiness_name, business_address, business_city, business_region, business_phone_number\n"
f.write(Headers)

my_url = 'https://www.yellowpages.com/search?search_terms=Stores&geo_location_terms=Chicago%2C%20IL&page={}'.format(page)

uClient = uReq(my_url)
page_html = uClient.read()
uClient.close()   

# html parsing
page_soup = soup(page_html, "html.parser")

# grabs each listing
containers = page_soup.findAll("div",{"class": "result"})

new = page_soup.findAll("a", {"class":"next ajax-page"})

for i in new:
    try:
        for container in containers:
            b_name = i.find("container.h2.span.text").get_text()
            b_addr = i.find("container.p.span.text").get_text()

            city_container = container.findAll("span",{"class": "locality"})
            b_city = i.find("city_container[0].text ").get_text()

            region_container = container.findAll("span",{"itemprop": "postalCode"})
            b_reg = i.find("region_container[0].text").get_text()

            phone_container = container.findAll("div",{"itemprop": "telephone"})
            b_phone = i.find("phone_container[0].text").get_text()

            print(b_name, b_addr, b_city, b_reg, b_phone)
            f.write(b_name + "," +b_addr + "," +b_city.replace(",", "|") + "," +b_reg + "," +b_phone + "\n")
    except: AttributeError
f.close()

使用python 3.6.3使用beautifulsoup4刮擦多个页面

0 个答案: