Here is my code for the scraper that is extracting the URL and corresponding comments from that particular page:
import scraperwiki
import lxml.html
from BeautifulSoup import BeautifulSoup
import urllib2
import re
for num in range(1,2):
html_page = urllib2.urlopen("https://success.salesforce.com/ideaSearch?keywords=error&pageNo="+str(num))
soup = BeautifulSoup(html_page)
for i in range(0,10):
for link in soup.findAll('a',{'id':'search:ForumLayout:searchForm:itemObj2:'+str(i)+':idea:recentIdeasComponent:profileIdeaTitle'}):
pageurl = link.get('href')
html = scraperwiki.scrape(pageurl)
root = lxml.html.fromstring(html)
for j in range(0,300):
for table in root.cssselect("span[id='ideaView:ForumLayout:ideaViewForm:cmtComp:ideaComments:cmtLoop:"+str(j)+":commentBodyOutput'] table"):
divx = table.cssselect("div[class='htmlDetailElementDiv']")
if len(divx)==1:
data = {
'URL' : pageurl,
'Comment' : divx[0].text_content()
}
print data
scraperwiki.sqlite.save(unique_keys=['URL'], data=data)
scraperwiki.sqlite.save(unique_keys=['Comment'], data=data)
When the data is saved to the scraperwiki datastore only the last comment from one URL is put into the table. What I would like is in the table for each URL to have all the comments saved. So, in one column there is the URL and in the second column there are all the comments from that URL, instead of just the last comment, which is what this code ends up with.
As I can see from your code, you put the data in the most inner for loop and assign it a new value every time. So when the for loop ends and goes to the save step, data will contain the last comment. I think you may use:
for i in range(0,10):
for link in soup.findAll('a',{'id':'search:ForumLayout:searchForm:itemObj2:'+str(i)+':idea:recentIdeasComponent:profileIdeaTitle'}):
pageurl = link.get('href')
html = scraperwiki.scrape(pageurl)
root = lxml.html.fromstring(html)
data = {'URL': pageurl, 'Comment':[]}
for j in range(0,300):
for table in root.cssselect("span[id='ideaView:ForumLayout:ideaViewForm:cmtComp:ideaComments:cmtLoop:"+str(j)+":commentBodyOutput'] table"):
divx = table.cssselect("div[class='htmlDetailElementDiv']")
if len(divx)==1:
data['Comment'].append(divx[0].text_content)
scraperwiki.sqlite.save(unique_keys=['URL'], data=data)
scraperwiki.sqlite.save(unique_keys=['Comment'], data=data)
Related
I have a next link which represent an exact graph I want to scrape: https://index.minfin.com.ua/ua/economy/index/svg.php?indType=1&fromYear=2010&acc=1
I'm simply can't understand is it a xml or svg graph and how to scrape data. I think I need to use bs4, requests but don't know the way to do that.
Anyone could help?
You will load HTML like this:
import requests
url = "https://index.minfin.com.ua/ua/economy/index/svg.php?indType=1&fromYear=2010&acc=1"
resp = requests.get(url)
data = resp.text
Then you will create a BeatifulSoup object with this HTML.
from bs4 import BeautifulSoup
soup = BeautifulSoup(html, features="html.parser")
After this, it is usually very subjective how to parse out what you want. The candidate codes may vary a lot. This is how I did it:
Using BeautifulSoup, I parsed all "rect"s and check if "onmouseover" exists in that rect.
rects = soup.svg.find_all("rect")
yx_points = []
for rect in rects:
if rect.has_attr("onmouseover"):
text = rect["onmouseover"]
x_start_index = text.index("'") + 1
y_finish_index = text[x_start_index:].index("'") + x_start_index
yx = text[x_start_index:y_finish_index].split()
print(text[x_start_index:y_finish_index])
yx_points.append(yx)
As you can see from the image below, I scraped onmouseover= part and get those 02.2015 155,1 parts.
Here, this is how yx_points looks like now:
[['12.2009', '100,0'], ['01.2010', '101,8'], ['02.2010', '103,7'], ...]
from bs4 import BeautifulSoup
import requests
import re
#First get all the text from the url.
url="https://index.minfin.com.ua/ua/economy/index/svg.php?indType=1&fromYear=2010&acc=1"
response = requests.get(url)
html = response.text
#Find all the tags in which the data is stored.
soup = BeautifulSoup(html, 'lxml')
texts = soup.findAll("rect")
final = []
for each in texts:
names = each.get('onmouseover')
try:
q = re.findall(r"'(.*?)'", names)
final.append(q[0])
except Exception as e:
print(e)
#The details are appended to the final variable
I'm trying to scrape the "team per game stats" table from this website using this code:
from urllib.request import urlopen as uo
from bs4 import BeautifulSoup as BS
import pandas as pd
url = 'https://www.basketball-reference.com/leagues/NBA_2020.html'
html = uo(url)
soup = BS(html, 'html.parser')
soup.findAll('tr')
headers = [th.getText() for th in soup.findAll('tr')]
headers = headers[1:]
print(headers)
rows = soup.findAll('tr')[1:]
team_stats = [[td.getText() for td in rows[i].findAll('td')]
for i in range(len(rows))]
stats = pd.DataFrame(team_stats, columns=headers)
But it returns this error:
AssertionError: 71 columns passed, passed data had 212 columns
The problem is that the data is hidden in a commented section of the HTML. The table you want to extract is rendered with Javascript in your browser. Requesting the page with requests or urllib just yields the raw HTML.
So be aware that you have to examine the source code of the page with "View page source" rather than the rendered page with "Inspect Element" if you search for the proper tags to find with BeautifulSoup.
Try this:
import requests
from bs4 import BeautifulSoup
import pandas as pd
url = 'https://www.basketball-reference.com/leagues/NBA_2020.html'
html = requests.get(url)
section_start = '<span class="section_anchor" id="team-stats-per_game_link" data-label="Team Per Game Stats">'
block_start = html.text.split(section_start)[1].split("<!--")[1]
block = block_start.split("-->")[0]
soup = BeautifulSoup(block)
data = [th.get_text(",") for th in soup.findAll('tr')]
header = data[0]
header = [x.strip() for x in header.split(",") if x.strip() !=""]
data = [x.split(",") for x in data[1:]]
pd.DataFrame(data, columns=header)
Explanation: You first need to find the commented section by simply splitting the raw HTML just before the section. You extract the section as text, convert to soup and then parse.
Please Help.
I want to get all the company names of each pages and they have 12 pages.
http://www.saramin.co.kr/zf_user/jobs/company-labs/list/page/1
http://www.saramin.co.kr/zf_user/jobs/company-labs/list/page/2
-- this website only changes the number.
So Here is my code so far.
Can I get just the title (company name) of 12 pages?
Thank you in advance.
from bs4 import BeautifulSoup
import requests
maximum = 0
page = 1
URL = 'http://www.saramin.co.kr/zf_user/jobs/company-labs/list/page/1'
response = requests.get(URL)
source = response.text
soup = BeautifulSoup(source, 'html.parser')
whole_source = ""
for page_number in range(1, maximum+1):
URL = 'http://www.saramin.co.kr/zf_user/jobs/company-labs/list/page/' + str(page_number)
response = requests.get(URL)
whole_source = whole_source + response.text
soup = BeautifulSoup(whole_source, 'html.parser')
find_company = soup.select("#content > div.wrap_analysis_data > div.public_con_box.public_list_wrap > ul > li:nth-child(13) > div > strong")
for company in find_company:
print(company.text)
---------Output of one page
---------page source :)
So, you want to remove all the headers and get only the string of the company name?
Basically, you can use the soup.findAll to find the list of company in the format like this:
<strong class="company"><span>중소기업진흥공단</span></strong>
Then you use the .find function to extract information from the <span> tag:
<span>중소기업진흥공단</span>
After that, you use .contents function to get the string from the <span> tag:
'중소기업진흥공단'
So you write a loop to do the same for each page, and make a list called company_list to store the results from each page and append them together.
Here's the code:
from bs4 import BeautifulSoup
import requests
maximum = 12
company_list = [] # List for result storing
for page_number in range(1, maximum+1):
URL = 'http://www.saramin.co.kr/zf_user/jobs/company-labs/list/page/{}'.format(page_number)
response = requests.get(URL)
print(page_number)
whole_source = response.text
soup = BeautifulSoup(whole_source, 'html.parser')
for entry in soup.findAll('strong', attrs={'class': 'company'}): # Finding all company names in the page
company_list.append(entry.find('span').contents[0]) # Extracting name from the result
The company_list will give you all the company names you want
I figured it out eventually. Thank you for your answer though!
image : code captured in jupyter notebook
Here is my final code.
from urllib.request import urlopen
from bs4 import BeautifulSoup
company_list=[]
for n in range(12):
url = 'http://www.saramin.co.kr/zf_user/jobs/company-labs/list/page/{}'.format(n+1)
webpage = urlopen(url)
source = BeautifulSoup(webpage,'html.parser',from_encoding='utf-8')
companys = source.findAll('strong',{'class':'company'})
for company in companys:
company_list.append(company.get_text().strip().replace('\n','').replace('\t','').replace('\r',''))
file = open('company_name1.txt','w',encoding='utf-8')
for company in company_list:
file.write(company+'\n')
file.close()
continuing on previous work to crawl all news result about query and to return title and url, I am refining the crawler to get all results from all pages in Google News. Current code seems can only return the 1st page Googel news search result. Would be grateful to know how to get all pages results. Many thanks!
my codes below:
import requests
from bs4 import BeautifulSoup
import time
import datetime
from random import randint
import numpy as np
import pandas as pd
query2Google = input("What do you want from Google News?\n")
def QGN(query2Google):
s = '"'+query2Google+'"' #Keywords for query
s = s.replace(" ","+")
date = str(datetime.datetime.now().date()) #timestamp
filename =query2Google+"_"+date+"_"+'SearchNews.csv' #csv filename
f = open(filename,"wb")
url = "http://www.google.com.sg/search?q="+s+"&tbm=nws&tbs=qdr:y" # URL for query of news results within one year and sort by date
#htmlpage = urllib2.urlopen(url).read()
time.sleep(randint(0, 2))#waiting
htmlpage = requests.get(url)
print("Status code: "+ str(htmlpage.status_code))
soup = BeautifulSoup(htmlpage.text,'lxml')
df = []
for result_table in soup.findAll("div", {"class": "g"}):
a_click = result_table.find("a")
#print ("-----Title----\n" + str(a_click.renderContents()))#Title
#print ("----URL----\n" + str(a_click.get("href"))) #URL
#print ("----Brief----\n" + str(result_table.find("div", {"class": "st"}).renderContents()))#Brief
#print ("Done")
df=np.append(df,[str(a_click.renderContents()).strip("b'"),str(a_click.get("href")).strip('/url?q='),str(result_table.find("div", {"class": "st"}).renderContents()).strip("b'")])
df = np.reshape(df,(-1,3))
df1 = pd.DataFrame(df,columns=['Title','URL','Brief'])
print("Search Crawl Done!")
df1.to_csv(filename, index=False,encoding='utf-8')
f.close()
return
QGN(query2Google)
There used to be an ajax api, but it's no longer avaliable .
Still , you can modify your script with a for loop if you want to get a number of pages , or a while loop if you want to get all pages .
Example :
url = "http://www.google.com.sg/search?q="+s+"&tbm=nws&tbs=qdr:y&start="
pages = 10 # the number of pages you want to crawl #
for next in range(0, pages*10, 10) :
page = url + str(next)
time.sleep(randint(1, 5)) # you may need longer than that #
htmlpage = requests.get(page) # you should add User-Agent and Referer #
print("Status code: " + str(htmlpage.status_code))
if htmlpage.status_code != 200 :
break # something went wrong #
soup = BeautifulSoup(htmlpage.text, 'lxml')
... process response here ...
next_page = soup.find('td', { 'class':'b', 'style':'text-align:left' })
if next_page is None or next_page.a is None :
break # there are no more pages #
Keep in mind that google doesn't like bots , you might get a ban .
You could add 'User-Agent' and 'Referer' in headers to simulate a web browser , and use time.sleep(random.uniform(2, 6)) to simulate a human ... or use selenium.
You can also add &num=25 to the end of your query and you'll get back a webpage with that number of results. In this example youll get back 25 google results back.
I am trying to scrape data from the PGA.com website to get a table of all of the golf courses in the United States. In my CSV table I want to include the Name of the golf course ,Address ,Ownership ,Website , Phone number. With this data I would like to geocode it and place into a map and have a local copy on my computer
I utilized Python and Beautiful Soup4 to extract my data. I have reached as far to extract the data and import it into a CSV but I am now having a problem of scraping data from multiple pages on the PGA website. I want to extract ALL THE GOLF COURSES but my script is limited only to one page I want to loop it in away that it will capture all data for golf courses from all pages found in the PGA site. There are about 18000 gold courses and 900 pages to capture data
Attached below is my script. I need help on creating code that will capture ALL data from the PGA website and not just one site but multiple. In this manner it will provide me with all the data of gold courses in the United States.
Here is my script below:
import csv
import requests
from bs4 import BeautifulSoup
url = "http://www.pga.com/golf-courses/search?searchbox=Course+Name&searchbox_zip=ZIP&distance=50&price_range=0&course_type=both&has_events=0"
r = requests.get(url)
soup = BeautifulSoup(r.content)
g_data1=soup.find_all("div",{"class":"views-field-nothing-1"})
g_data2=soup.find_all("div",{"class":"views-field-nothing"})
courses_list=[]
for item in g_data2:
try:
name=item.contents[1].find_all("div",{"class":"views-field-title"})[0].text
except:
name=''
try:
address1=item.contents[1].find_all("div",{"class":"views-field-address"})[0].text
except:
address1=''
try:
address2=item.contents[1].find_all("div",{"class":"views-field-city-state-zip"})[0].text
except:
address2=''
try:
website=item.contents[1].find_all("div",{"class":"views-field-website"})[0].text
except:
website=''
try:
Phonenumber=item.contents[1].find_all("div",{"class":"views-field-work-phone"})[0].text
except:
Phonenumber=''
course=[name,address1,address2,website,Phonenumber]
courses_list.append(course)
with open ('filename5.csv','wb') as file:
writer=csv.writer(file)
for row in courses_list:
writer.writerow(row)
#for item in g_data1:
#try:
#print item.contents[1].find_all("div",{"class":"views-field-counter"})[0].text
#except:
#pass
#try:
#print item.contents[1].find_all("div",{"class":"views-field-course-type"})[0].text
#except:
#pass
#for item in g_data2:
#try:
#print item.contents[1].find_all("div",{"class":"views-field-title"})[0].text
#except:
#pass
#try:
#print item.contents[1].find_all("div",{"class":"views-field-address"})[0].text
#except:
#pass
#try:
#print item.contents[1].find_all("div",{"class":"views-field-city-state-zip"})[0].text
#except:
#pass
This script only captures 20 at a time and I want to capture all in one script which account for 18000 golf courses and 900 pages to scrape form.
The PGA website's search have multiple pages, the url follows the pattern:
http://www.pga.com/golf-courses/search?page=1 # Additional info after page parameter here
this means you can read the content of the page, then change the value of page by 1, and read the the next page.... and so on.
import csv
import requests
from bs4 import BeautifulSoup
for i in range(907): # Number of pages plus one
url = "http://www.pga.com/golf-courses/search?page={}&searchbox=Course+Name&searchbox_zip=ZIP&distance=50&price_range=0&course_type=both&has_events=0".format(i)
r = requests.get(url)
soup = BeautifulSoup(r.content)
# Your code for each individual page here
if you still read this post , you can try this code too....
from urllib.request import urlopen
from bs4 import BeautifulSoup
file = "Details.csv"
f = open(file, "w")
Headers = "Name,Address,City,Phone,Website\n"
f.write(Headers)
for page in range(1,5):
url = "http://www.pga.com/golf-courses/search?page={}&searchbox=Course%20Name&searchbox_zip=ZIP&distance=50&price_range=0&course_type=both&has_events=0".format(page)
html = urlopen(url)
soup = BeautifulSoup(html,"html.parser")
Title = soup.find_all("div", {"class":"views-field-nothing"})
for i in Title:
try:
name = i.find("div", {"class":"views-field-title"}).get_text()
address = i.find("div", {"class":"views-field-address"}).get_text()
city = i.find("div", {"class":"views-field-city-state-zip"}).get_text()
phone = i.find("div", {"class":"views-field-work-phone"}).get_text()
website = i.find("div", {"class":"views-field-website"}).get_text()
print(name, address, city, phone, website)
f.write("{}".format(name).replace(",","|")+ ",{}".format(address)+ ",{}".format(city).replace(",", " ")+ ",{}".format(phone) + ",{}".format(website) + "\n")
except: AttributeError
f.close()
where it is written range(1,5) just change that with 0,to the last page , and you will get all details in CSV, i tried very hard to get your data in proper format but it's hard:).
You're putting a link to a single page, it's not going to iterate through each one on its own.
Page 1:
url = "http://www.pga.com/golf-courses/search?searchbox=Course+Name&searchbox_zip=ZIP&distance=50&price_range=0&course_type=both&has_events=0"
Page 2:
http://www.pga.com/golf-courses/search?page=1&searchbox=Course%20Name&searchbox_zip=ZIP&distance=50&price_range=0&course_type=both&has_events=0
Page 907:
http://www.pga.com/golf-courses/search?page=906&searchbox=Course%20Name&searchbox_zip=ZIP&distance=50&price_range=0&course_type=both&has_events=0
Since you're running for page 1 you'll only get 20. You'll need to create a loop that'll run through each page.
You can start off by creating a function that does one page then iterate that function.
Right after the search? in the url, starting at page 2, page=1 begins increasing until page 907 where it's page=906.
I noticed that the first solution had a repetition of the first instance, that is because the 0 page and 1 page is the same page. This is resolved by specifying the start page in the range function. Example below...
for i in range(1, 907): #Number of pages plus one
url = "http://www.pga.com/golf-courses/search?page={}&searchbox=Course+Name&searchbox_zip=ZIP&distance=50&price_range=0&course_type=both&has_events=0".format(i)
r = requests.get(url)
soup = BeautifulSoup(r.content, "html5lib") #Can use whichever parser you prefer
# Your code for each individual page here
Had this same exact problem and the solutions above did not work. I solved mine by accounting for cookies. A requests session helps. Create a session and it'll pull all the pages you need by inserting a cookie to all the numbered pages.
import csv
import requests
from bs4 import BeautifulSoup
url = "http://www.pga.com/golf-courses/search?searchbox=Course+Name&searchbox_zip=ZIP&distance=50&price_range=0&course_type=both&has_events=0"
s = requests.Session()
r = s.get(url)
The PGA website has changed this question has been asked.
It seems they organize all courses by: State > City > Course
In light of this change and the popularity of this question, here's how I'd solve this problem today.
Step 1 - Import everything we'll need:
import time
import random
from gazpacho import Soup # https://github.com/maxhumber/gazpacho
from tqdm import tqdm # to keep track of progress
Step 2 - Scrape all the state URL endpoints:
URL = "https://www.pga.com"
def get_state_urls():
soup = Soup.get(URL + "/play")
a_tags = soup.find("ul", {"data-cy": "states"}, mode="first").find("a")
state_urls = [URL + a.attrs['href'] for a in a_tags]
return state_urls
state_urls = get_state_urls()
Step 3 - Write a function to scrape all the city links:
def get_state_cities(state_url):
soup = Soup.get(state_url)
a_tags = soup.find("ul", {"data-cy": "city-list"}).find("a")
state_cities = [URL + a.attrs['href'] for a in a_tags]
return state_cities
state_url = state_urls[0]
city_links = get_state_cities(state_url)
Step 4 - Write a function to scrape all of the courses:
def get_courses(city_link):
soup = Soup.get(city_link)
courses = soup.find("div", {"class": "MuiGrid-root MuiGrid-item MuiGrid-grid-xs-12 MuiGrid-grid-md-6"}, mode="all")
return courses
city_link = city_links[0]
courses = get_courses(city_link)
Step 5 - Write a function to parse all the useful info about a course:
def parse_course(course):
return {
"name": course.find("h5", mode="first").text,
"address": course.find("div", {'class': "jss332"}, mode="first").strip(),
"url": course.find("a", mode="first").attrs["href"]
}
course = courses[0]
parse_course(course)
Step 6 - Loop through everything and save:
all_courses = []
for state_url in tqdm(state_urls):
city_links = get_state_cities(state_url)
time.sleep(random.uniform(1, 10) / 10)
for city_link in city_links:
courses = get_courses(city_link)
time.sleep(random.uniform(1, 10) / 10)
for course in courses:
info = parse_course(course)
all_courses.append(info)