How to scrape a website using following pagination in bs4? - python

I have a script that scrapes a specific website, where the number of a page is defined with ?start={}. This site.
This is my script:
from bs4 import BeautifulSoup
from urllib.request import urlopen
def parse():
for i in range(0, 480, 5):
html = urlopen('http://rl.odessa.ua/index.php/ru/poslednie-novosti?start={}'.format(i))
soup = BeautifulSoup(html, 'lxml')
for article in soup.findAll('article', class_ = 'item'):
try:
print('\t' + article.find('h1').find('a').get_text())
print(article.find('p').get_text() + '\n' + '*'*80)
except AttributeError as e:
print(e)
parse()
At the bottom of the page is located div.pagination with a.next. Here's a screenshot.
Is it a bad practise using range() instead of pagination? Anyway, please help me to rewrite the code above using pagination.

Whichever method works for you is fine, but locating the next button would make things easier. It could be done as follows:
from bs4 import BeautifulSoup
from urllib.request import urlopen
def parse():
base_url = 'http://rl.odessa.ua/index.php'
url = 'http://rl.odessa.ua/index.php/ru/poslednie-novosti?start=0'
while True:
html = urlopen(url)
soup = BeautifulSoup(html, 'lxml')
for article in soup.findAll('article', class_ = 'item'):
try:
print('\t' + article.find('h1').find('a').get_text())
print(article.find('p').get_text() + '\n' + '*'*80)
except AttributeError as e:
print(e)
next_button = soup.find('a', class_='next', href=True)
if next_button:
url = base_url + next_button['href']
else:
break
parse()

Related

How to extracting content from pagination next button?

This is the website I am trying to scrape:
(https://www.jurongpoint.com.sg/store-directory/?level=&cate=Food+%26+Beverage)
Below is the code that I have tried,but it repetitively return me first page and third page.
from bs4 import BeautifulSoup
from urllib.request import urlopen
def parse():
base_url = 'https://www.jurongpoint.com.sg/store-directory/?level=&cate=Food+%26+Beverage'
url="https://www.jurongpoint.com.sg/store-directory/?level=&cate=Food+%26+Beverage&page=3"
while True:
html = urlopen(url)
soup = BeautifulSoup(html ,"html.parser")
for link in soup.find_all('div',class_='entry-content'):
try:
shops=soup.find_all('div',class_="col-9")
names=soup.find_all('tr',class_="clickable")
for n, k in zip(names, shops):
name = n.find_all('td')[1].text.replace(' ','')
desc = k.text.replace(' ','')
print(name + "\n")
print(desc)
except AttributeError as e:
print(e)
next_button = soup.find('a', href=True)
if next_button:
url = base_url + next_button['href']
else:
break
parse()
Select your elements more specific, used css selectors here to get the <a> that is child of an element with class="PagedList-skipToNext" :
next_button = soup.select_one('.PagedList-skipToNext a')
Also check the results of your selection, base_url is not needed here:
url = next_button.get('href')
Example
from bs4 import BeautifulSoup
import requests
def parse():
url = 'https://www.jurongpoint.com.sg/store-directory/?level=&cate=Food+%26+Beverage'
while True:
soup = BeautifulSoup(requests.get(url).text)
print(url) ## to see what you are working on or enter code that should be performed
next_button = soup.select_one('.PagedList-skipToNext a')
if next_button:
url = next_button.get('href')
else:
break
parse()
Output
https://www.jurongpoint.com.sg/store-directory/?level=&cate=Food+%26+Beverage
http://www.jurongpoint.com.sg/store-directory/?level=&cate=Food+%26+Beverage&page=2
http://www.jurongpoint.com.sg/store-directory/?level=&cate=Food+%26+Beverage&page=3
http://www.jurongpoint.com.sg/store-directory/?level=&cate=Food+%26+Beverage&page=4
http://www.jurongpoint.com.sg/store-directory/?level=&cate=Food+%26+Beverage&page=5
http://www.jurongpoint.com.sg/store-directory/?level=&cate=Food+%26+Beverage&page=6
http://www.jurongpoint.com.sg/store-directory/?level=&cate=Food+%26+Beverage&page=7
http://www.jurongpoint.com.sg/store-directory/?level=&cate=Food+%26+Beverage&page=8
http://www.jurongpoint.com.sg/store-directory/?level=&cate=Food+%26+Beverage&page=9
http://www.jurongpoint.com.sg/store-directory/?level=&cate=Food+%26+Beverage&page=10
http://www.jurongpoint.com.sg/store-directory/?level=&cate=Food+%26+Beverage&page=11
http://www.jurongpoint.com.sg/store-directory/?level=&cate=Food+%26+Beverage&page=12
http://www.jurongpoint.com.sg/store-directory/?level=&cate=Food+%26+Beverage&page=13
http://www.jurongpoint.com.sg/store-directory/?level=&cate=Food+%26+Beverage&page=14

Using BeautifulSoup to find links related to specific keyword

I have to modify this code so the scraping keeps only the links that contain a specific keyword. In my case I'm scraping a newspaper page to find news related to the term 'Brexit'.
I've tried modifying the method parse_links so it only keeps the links (or 'a' tags), that contain 'Brexit' in them, but it doesn't seem to work.
Where should i place the condition?
import requests
from bs4 import BeautifulSoup
from queue import Queue, Empty
from concurrent.futures import ThreadPoolExecutor
from urllib.parse import urljoin, urlparse
class MultiThreadScraper:
def __init__(self, base_url):
self.base_url = base_url
self.root_url = '{}://{}'.format(urlparse(self.base_url).scheme, urlparse(self.base_url).netloc)
self.pool = ThreadPoolExecutor(max_workers=20)
self.scraped_pages = set([])
self.to_crawl = Queue(10)
self.to_crawl.put(self.base_url)
def parse_links(self, html):
soup = BeautifulSoup(html, 'html.parser')
links = soup.find_all('a', href=True)
for link in links:
url = link['href']
if url.startswith('/') or url.startswith(self.root_url):
url = urljoin(self.root_url, url)
if url not in self.scraped_pages:
self.to_crawl.put(url)
def scrape_info(self, html):
return
def post_scrape_callback(self, res):
result = res.result()
if result and result.status_code == 200:
self.parse_links(result.text)
self.scrape_info(result.text)
def scrape_page(self, url):
try:
res = requests.get(url, timeout=(3, 30))
return res
except requests.RequestException:
return
def run_scraper(self):
while True:
try:
target_url = self.to_crawl.get(timeout=60)
if target_url not in self.scraped_pages:
print("Scraping URL: {}".format(target_url))
self.scraped_pages.add(target_url)
job = self.pool.submit(self.scrape_page, target_url)
job.add_done_callback(self.post_scrape_callback)
except Empty:
return
except Exception as e:
print(e)
continue
if __name__ == '__main__':
s = MultiThreadScraper("https://elpais.com/")
s.run_scraper()
You need to import re module to get the specific text value.Try the below code.
import re
links = soup.find_all('a', text=re.compile("Brexit"))
This should return links which contains only Brexit.
You can get text of the element by using method getText() and check, if string actually contain "Brexit":
if "Brexit" in link.getText().split():
url = link["href"]
I added a check in this function. See if that does the rick for you:
def parse_links(self, html):
soup = BeautifulSoup(html, 'html.parser')
links = soup.find_all('a', href=True)
for link in links:
if 'BREXIT' in link.text.upper(): #<------ new if statement
url = link['href']
if url.startswith('/') or url.startswith(self.root_url):
url = urljoin(self.root_url, url)
if url not in self.scraped_pages:
self.to_crawl.put(url)

Scraping multiple pages with beautifulsoup4 using python 3.6.3

I am trying to loop through multiple pages and my code doesn't extract anything. I am kind of new to scraping so bear with me. I made a container so I can target each listing. I also made a variable to target the anchor tag that you would press to go to the next page. I would really appreciate any help I could get. Thanks.
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()
If using BS4 try : find_all
Try dropping into a trace using import pdb;pdb.set_trace() and try to debug what is being selected in the for loop.
Also, some content may be hidden if it is loaded via javascript.
Each anchor tag or href for "clicking" is just another network request, and if you plan to follow the link consider slowing down the number of requests in between each request, so you don't get blocked.
You can try like the below script. It will traverse different pages through pagination and collect name and phone numbers from each container.
import requests
from bs4 import BeautifulSoup
my_url = "https://www.yellowpages.com/search?search_terms=Stores&geo_location_terms=Chicago%2C%20IL&page={}"
for link in [my_url.format(page) for page in range(1,5)]:
res = requests.get(link)
soup = BeautifulSoup(res.text, "lxml")
for item in soup.select(".info"):
try:
name = item.select(".business-name [itemprop='name']")[0].text
except Exception:
name = ""
try:
phone = item.select("[itemprop='telephone']")[0].text
except Exception:
phone = ""
print(name,phone)

Pagination with BeautifulSoup

I am trying to get some data from the following website. https://www.drugbank.ca/drugs
For every drug in the table, I will need to go deeply and have the name and some other specific features like categories, structured indication (please click on drug name to see the features I will use).
I wrote the following code but the issue that I can't make my code handle pagination (as you see there more than 2000 pages!).
import requests
from bs4 import BeautifulSoup
def drug_data():
url = 'https://www.drugbank.ca/drugs/'
r = requests.get(url)
soup = BeautifulSoup(r.text ,"lxml")
for link in soup.select('name-head a'):
href = 'https://www.drugbank.ca/drugs/' + link.get('href')
pages_data(href)
def pages_data(item_url):
r = requests.get(item_url)
soup = BeautifulSoup(r.text, "lxml")
g_data = soup.select('div.content-container')
for item in g_data:
print item.contents[1].text
print item.contents[3].findAll('td')[1].text
try:
print item.contents[5].findAll('td',{'class':'col-md-2 col-sm-4'})
[0].text
except:
pass
print item_url
drug_data()
How can I scrape all of the data and handle pagination properly?
This page uses almost the same url for all pages so you can use for loop to generate them
def drug_data(page_number):
url = 'https://www.drugbank.ca/drugs/?page=' + str(page_number)
#... rest ...
# --- later ---
for x in range(1, 2001):
drug_data(x)
Or using while and try/except to get more then 2000 pages
def drug_data(page_number):
url = 'https://www.drugbank.ca/drugs/?page=' + str(page_number)
#... rest ...
# --- later ---
page = 0
while True:
try:
page += 1
drug_data(page)
except Exception as ex:
print(ex)
print("probably last page:", page)
break # exit `while` loop
You can also find url to next page in HTML
<a rel="next" class="page-link" href="/drugs?approved=1&c=name&d=up&page=2">›</a>
so you can use BeautifulSoup to get this link and use it.
It displays current url, finds link to next page (using class="page-link" rel="next") and loads it
import requests
from bs4 import BeautifulSoup
def drug_data():
url = 'https://www.drugbank.ca/drugs/'
while url:
print(url)
r = requests.get(url)
soup = BeautifulSoup(r.text ,"lxml")
#data = soup.select('name-head a')
#for link in data:
# href = 'https://www.drugbank.ca/drugs/' + link.get('href')
# pages_data(href)
# next page url
url = soup.findAll('a', {'class': 'page-link', 'rel': 'next'})
print(url)
if url:
url = 'https://www.drugbank.ca' + url[0].get('href')
else:
break
drug_data()
BTW: never use except:pass because you can have error which you didn't expect and you will not know why it doesn't work. Better display error
except Exception as ex:
print('Error:', ex)

Get all urls from a website using python

I am learning to build web crawlers and currently working on getting all urls from a site. I have been playing around and don't have the same code as I did before but I have been able to get all the links but my issues is the recursion I need to do the same things over and over but what I think my issue is the recursion what it is doing is right for the code I have written. My code is bellow
#!/usr/bin/python
import urllib2
import urlparse
from BeautifulSoup import BeautifulSoup
def getAllUrl(url):
page = urllib2.urlopen( url ).read()
urlList = []
try:
soup = BeautifulSoup(page)
soup.prettify()
for anchor in soup.findAll('a', href=True):
if not 'http://' in anchor['href']:
if urlparse.urljoin('http://bobthemac.com', anchor['href']) not in urlList:
urlList.append(urlparse.urljoin('http://bobthemac.com', anchor['href']))
else:
if anchor['href'] not in urlList:
urlList.append(anchor['href'])
length = len(urlList)
for url in urlList:
getAllUrl(url)
return urlList
except urllib2.HTTPError, e:
print e
if __name__ == "__main__":
urls = getAllUrl('http://bobthemac.com')
for x in urls:
print x
What I am trying to achieve is get all the urls for a site with the current set-up the program runs till it runs out of memory all I want is to get the urls from a site. Does anyone have any idea on how to do this think I have the right idea just need some small changes to the code.
EDIT
For those of you what are intrested bellow is my working code that gets all the urs for the site someone might find it useful. It's not the best code and does need some work but with some work it could be quite good.
#!/usr/bin/python
import urllib2
import urlparse
from BeautifulSoup import BeautifulSoup
def getAllUrl(url):
urlList = []
try:
page = urllib2.urlopen( url ).read()
soup = BeautifulSoup(page)
soup.prettify()
for anchor in soup.findAll('a', href=True):
if not 'http://' in anchor['href']:
if urlparse.urljoin('http://bobthemac.com', anchor['href']) not in urlList:
urlList.append(urlparse.urljoin('http://bobthemac.com', anchor['href']))
else:
if anchor['href'] not in urlList:
urlList.append(anchor['href'])
return urlList
except urllib2.HTTPError, e:
urlList.append( e )
if __name__ == "__main__":
urls = getAllUrl('http://bobthemac.com')
fullList = []
for x in urls:
listUrls = list
listUrls = getAllUrl(x)
try:
for i in listUrls:
if not i in fullList:
fullList.append(i)
except TypeError, e:
print 'Woops wrong content passed'
for i in fullList:
print i
I think this works:
#!/usr/bin/python
import urllib2
import urlparse
from BeautifulSoup import BeautifulSoup
def getAllUrl(url):
try:
page = urllib2.urlopen( url ).read()
except:
return []
urlList = []
try:
soup = BeautifulSoup(page)
soup.prettify()
for anchor in soup.findAll('a', href=True):
if not 'http://' in anchor['href']:
if urlparse.urljoin(url, anchor['href']) not in urlList:
urlList.append(urlparse.urljoin(url, anchor['href']))
else:
if anchor['href'] not in urlList:
urlList.append(anchor['href'])
length = len(urlList)
return urlList
except urllib2.HTTPError, e:
print e
def listAllUrl(urls):
for x in urls:
print x
urls.remove(x)
urls_tmp = getAllUrl(x)
for y in urls_tmp:
urls.append(y)
if __name__ == "__main__":
urls = ['http://bobthemac.com']
while(urls.count>0):
urls = getAllUrl('http://bobthemac.com')
listAllUrl(urls)
In you function getAllUrl, you call getAllUrl again in a for loop, it makes a recursion.
Elements will never be moved out once put into urlList, so urlList will never be empty, and then, the recursion will never break up.
That's why your program will never end up util out of memory.

Categories