Python - 为什么这个数据被写入文件不正确？

Question

只有第一个结果正在写入csv，每行包含一个url的一个字母。这不是所有的URL都被写入，每行一个。

我在这段代码的最后一部分没有做什么，导致只用结果之一而不是所有结果写入cvs？

import requests 
from bs4 import BeautifulSoup 
import csv 

def grab_listings(): 
    url = ("http://www.gym-directory.com/listing-category/gyms-fitness-centres/") 
    r = requests.get(url) 
    soup = BeautifulSoup(r.text, 'html.parser') 
    l_area = soup.find("div", {"class":"wlt_search_results"}) 
    for elem in l_area.findAll("a", {"class":"frame"}): 
     return elem["href"] 

    url = ("http://www.gym-directory.com/listing-category/gyms-fitness-centres/page/2/") 
    r = requests.get(url) 
    soup = BeautifulSoup(r.text, 'html.parser') 
    l_area = soup.find("div", {"class":"wlt_search_results"}) 
    for elem in l_area.findAll("a", {"class":"frame"}): 
     return elem["href"] 

    url = ("http://www.gym-directory.com/listing-category/gyms-fitness-centres/page/3/") 
    r = requests.get(url) 
    soup = BeautifulSoup(r.text, 'html.parser') 
    l_area = soup.find("div", {"class":"wlt_search_results"}) 
    for elem in l_area.findAll("a", {"class":"frame"}): 
     return elem["href"] 

    url = ("http://www.gym-directory.com/listing-category/gyms-fitness-centres/page/4/") 
    r = requests.get(url) 
    soup = BeautifulSoup(r.text, 'html.parser') 
    l_area = soup.find("div", {"class":"wlt_search_results"}) 
    for elem in l_area.findAll("a", {"class":"frame"}): 
     return elem["href"] 

    url = ("http://www.gym-directory.com/listing-category/gyms-fitness-centres/page/5/") 
    r = requests.get(url) 
    soup = BeautifulSoup(r.text, 'html.parser') 
    l_area = soup.find("div", {"class":"wlt_search_results"}) 
    for elem in l_area.findAll("a", {"class":"frame"}): 
     return elem["href"] 

    url = ("http://www.gym-directory.com/listing-category/gyms-fitness-centres/page/6/") 
    r = requests.get(url) 
    soup = BeautifulSoup(r.text, 'html.parser') 
    l_area = soup.find("div", {"class":"wlt_search_results"}) 
    for elem in l_area.findAll("a", {"class":"frame"}): 
     return elem["href"] 

    url = ("http://www.gym-directory.com/listing-category/gyms-fitness-centres/page/7/") 
    r = requests.get(url) 
    soup = BeautifulSoup(r.text, 'html.parser') 
    l_area = soup.find("div", {"class":"wlt_search_results"}) 
    for elem in l_area.findAll("a", {"class":"frame"}): 
     return elem["href"] 

    url = ("http://www.gym-directory.com/listing-category/gyms-fitness-centres/page/8/") 
    r = requests.get(url) 
    soup = BeautifulSoup(r.text, 'html.parser') 
    l_area = soup.find("div", {"class":"wlt_search_results"}) 
    for elem in l_area.findAll("a", {"class":"frame"}): 
     return elem["href"] 

    url = ("http://www.gym-directory.com/listing-category/gyms-fitness-centres/page/9/") 
    r = requests.get(url) 
    soup = BeautifulSoup(r.text, 'html.parser') 
    l_area = soup.find("div", {"class":"wlt_search_results"}) 
    for elem in l_area.findAll("a", {"class":"frame"}): 
     return elem["href"] 

l = grab_listings() 


with open ("gyms.csv", "wb") as file: 
     writer = csv.writer(file) 
     for row in l: 
      writer.writerow(row) 

Answer 1

简体：

import requests 
from bs4 import BeautifulSoup 
import csv 


def grab_listings(): 
    for i in range(0, 5): 
     url = "http://www.gym-directory.com/listing-category/gyms-fitness-centres/page/{}/" 

     r = requests.get(url.format(i + 1)) 
     soup = BeautifulSoup(r.text, 'html.parser') 
     l_area = soup.find("div", {"class": "wlt_search_results"}) 

     for elem in l_area.findAll("a", {"class": "frame"}): 
      yield elem["href"] 

l = grab_listings() 


with open("gyms.csv", "w") as file: 
    writer = csv.writer(file) 
    for row in l: 
     writer.writerow(row) 

Answer 2

所以我重构你的代码了一下，我认为它应该工作，你会想到它现在：

import requests 
from bs4 import BeautifulSoup 
import csv 


def grab_listings(page_idx): 
    ret = [] 
    url = ("http://www.gym-directory.com/listing-category/gyms-fitness-centres/" 
      "page/{}/").format(page_idx) # the index of the page will be inserted here 
    r = requests.get(url) 
    soup = BeautifulSoup(r.text, 'html.parser') 
    l_area = soup.find("div", {"class": "wlt_search_results"}) 
    for elem in l_area.findAll("a", {"class": "frame"}): 
     # be sure to add all your results to a list and return it, 
     # if you return here then you will only get the first result 
     ret.append(elem["href"]) 
    return ret 


def main(): 
    l = [] # this will be a list of lists 
    # call the function 9 times here with idx from 1 till 9 
    for page_idx in range(1, 10): 
     l.append(grab_listings(page_idx)) 
    print l 

    with open("gyms.csv", "wb") as f: 
     writer = csv.writer(f) 
     for row in l: 
      # be sure that your row is a list here, if it is only 
      # a string all characters will be seperated by a comma. 
      writer.writerow(row) 

# for writing each URL in one line separated by commas at the end 
# with open("gyms.csv", "wb") as f: 
#  for row in l: 
#   string_to_write = ',\n'.join(row) 
#   f.write(string_to_write) 

if __name__ == '__main__': 
    main() 

我添加了一些意见的代码并希望它足够说明问题。如果不是只是要求:)