My intent is to run a scrapy crawler on this web page: http://visit.rio/en/o-que-fazer/outdoors/ . However, there's some resources on id="container" that load by a JavaScript button ("VER MAIS") click only. I've read some stuffs about selenium, but I've got nothing.
You read right, your best bet would be scrapy + selenium using a Firefox browser or a headless one like PhantomJS for faster scraping.
Example adapted from https://stackoverflow.com/a/17979285/2781701
import scrapy
from selenium import webdriver
class ProductSpider(scrapy.Spider):
name = "product_spider"
allowed_domains = ['visit.rio']
start_urls = ['http://visit.rio/en/o-que-fazer/outdoors']
def __init__(self):
self.driver = webdriver.Firefox()
def parse(self, response):
self.driver.get(response.url)
while True:
next = self.driver.find_element_by_xpath('//div[#id="show_more"]/a')
try:
next.click()
# get the data and write it to scrapy items
except:
break
self.driver.close()
Related
I want to parse all URL's in Git repository where any e-mails occur.
I use https://grep.app
The code:
from bs4 import BeautifulSoup
from selenium import webdriver
url = 'https://grep.app/search?current=100&q=%40gmail.com'
chrome = "/home/dev/chromedriver"
browser = webdriver.Chrome(executable_path=chrome)
browser.get(url)
html = browser.page_source
soup = BeautifulSoup(html, 'lxml')
tags = soup.select('a')
print(tags)
When code started, Chrome started and page with results are loaded and in Developers tools in Chrome, in source code I can see a lot of A and HREF for URL's.
Source from page
Like:
lib/plugins/revert/lang/eu/lang.php
But my code return only "tags" from footer:
"[<span class="slashes">//</span>grep.app, Contact]"
As I understand something wrong with JS parsing.
Please advise what I'm doing wrong?
Code:
from bs4 import BeautifulSoup
from selenium import webdriver
url = 'https://grep.app/search?current=100&q=%40gmail.com'
chrome = "/home/dev/chromedriver"
browser = webdriver.Chrome(executable_path=chrome)
browser.get(url)
html = browser.page_source
soup = BeautifulSoup(html, 'lxml')
links = []
tags = soup.find_all('a', href=True)
for tag in tags:
links.append(tag['href'])
print(links)
Output:
['/', 'mailto:hello#grep.app']
I would like to extract the market information from the following url and all of its subsequent pages:
https://uk.reuters.com/investing/markets/index/.FTSE?sortBy=&sortDir=&pn=1
I have successfully parsed the data that I want from the first page using some code from the following url:
https://impythonist.wordpress.com/2015/01/06/ultimate-guide-for-scraping-javascript-rendered-web-pages
I have also been able to parse out the url for the next page to feed into a loop in order to grab data from the next page. The problem is it crashes before the next page loads for a reason I don't fully understand.
I have a hunch that the class that I have borrowed from 'impythonist' may be causing the problem. I don't know enough object orientated programming to work out the problem. Here is my code, much of which is borrowed from the the url above:
import sys
from PyQt4.QtGui import *
from PyQt4.QtCore import *
from PyQt4.QtWebKit import *
from lxml import html
import re
from bs4 import BeautifulSoup
class Render(QWebPage):
def __init__(self, url):
self.app = QApplication(sys.argv)
QWebPage.__init__(self)
self.loadFinished.connect(self._loadFinished)
self.mainFrame().load(QUrl(url))
self.app.exec_()
def _loadFinished(self, result):
self.frame = self.mainFrame()
self.app.quit()
base_url='https://uk.reuters.com'
complete_next_page='https://uk.reuters.com/investing/markets/index/.FTSE?sortBy=&sortDir=&pn=1'
#LOOP TO RENDER PAGES AND GRAB DATA
while complete_next_page != '':
print ('NEXT PAGE: ',complete_next_page, '\n')
r = Render(complete_next_page) # USE THE CLASS TO RENDER JAVASCRIPT FROM PAGE
result = r.frame.toHtml() # ERROR IS THROWN HERE ON 2nd PAGE
# PARSE THE HTML
soup = BeautifulSoup(result, 'lxml')
row_data=soup.find('div', attrs={'class':'column1 gridPanel grid8'})
print (len(row_data))
# PARSE ALL ROW DATA
stripe_rows=row_data.findAll('tr', attrs={'class':'stripe'})
non_stripe_rows=row_data.findAll('tr', attrs={'class':''})
print (len(stripe_rows))
print (len(non_stripe_rows))
# PARSE SPECIFIC ROW DATA FROM INDEX COMPONENTS
#non_stripe_rows: from 4 to 18 (inclusive) contain data
#stripe_rows: from 2 to 16 (inclusive) contain data
i=2
while i < len(stripe_rows):
print('CURRENT LINE IS: ',str(i))
print(stripe_rows[i])
print('###############################################')
print(non_stripe_rows[i+2])
print('\n')
i+=1
#GETS LINK TO NEXT PAGE
next_page=str(soup.find('div', attrs={'class':'pageNavigation'}).find('li', attrs={'class':'next'}).find('a')['href']) #GETS LINK TO NEXT PAGE WORKS
complete_next_page=base_url+next_page
I have annotated the bits of code that I have written and understand but I don't really know what's going on in the 'Render' class enough to diagnose the error? Unless its something else?
Here is the error:
result = r.frame.toHtml()
AttributeError: 'Render' object has no attribute 'frame'
I don't need to keep the information in the class once I have parsed it out so I was thinking perhaps it could be cleared or reset somehow and then updated to hold the new url information from page 2:n but I have no idea how to do this?
Alternatively if anyone knows another way to grab this specific data from this page and the following ones then that would be equally helpful?
Many thanks in advance.
How about using selenium and phantomjs instead of PyQt.
You can easily get selenium by executing "pip install selenium".
If you use Mac you can get phantomjs by executing "brew install phantomjs".
If your PC is Windows use choco instead of brew, or Ubuntu use apt-get.
from selenium import webdriver
from bs4 import BeautifulSoup
base_url = "https://uk.reuters.com"
first_page = "/business/markets/index/.FTSE?sortBy=&sortDir=&pn=1"
browser = webdriver.PhantomJS()
# PARSE THE HTML
browser.get(base_url + first_page)
soup = BeautifulSoup(browser.page_source, "lxml")
row_data = soup.find('div', attrs={'class':'column1 gridPanel grid8'})
# PARSE ALL ROW DATA
stripe_rows = row_data.findAll('tr', attrs={'class':'stripe'})
non_stripe_rows = row_data.findAll('tr', attrs={'class':''})
print(len(stripe_rows), len(non_stripe_rows))
# GO TO THE NEXT PAGE
next_button = soup.find("li", attrs={"class":"next"})
while next_button:
next_page = next_button.find("a")["href"]
browser.get(base_url + next_page)
soup = BeautifulSoup(browser.page_source, "lxml")
row_data = soup.find('div', attrs={'class':'column1 gridPanel grid8'})
stripe_rows = row_data.findAll('tr', attrs={'class':'stripe'})
non_stripe_rows = row_data.findAll('tr', attrs={'class':''})
print(len(stripe_rows), len(non_stripe_rows))
next_button = soup.find("li", attrs={"class":"next"})
# DONT FORGET THIS!!
browser.quit()
I know the code above is not efficient (too slow I feel), but I think that it will bring you the results you desire. In addition, if the web page you want to scrape does not use Javascript, even PhantomJS and selenium are unnecessary. You can use the requests module. However, since I wanted to show you the contrast with PyQt, I used PhantomJS and Selenium in this answer.
I am trying to use Selenium and PhantomJS to get the dynamic content of a website. Here's my code
class judge(Spider):
name = "judge"
start_urls = ["http://wenshu.court.gov.cn/List/List?sorttype=1&conditions=searchWord+2+AJLX++%E6%A1%88%E4%BB%B6%E7%B1%BB%E5%9E%8B:%E6%B0%91%E4%BA%8B%E6%A1%88%E4%BB%B6"]
def init_driver(self):
driver = webdriver.Chrome()
return driver
def parse(self,response):
driver = self.init_driver()
driver.get(self.start_urls[0])
sel = Selector(text=driver.page_source)
self.logger.info(u'---------------Parsing----------------')
print sel.xpath("//div[#class='dataItem'][1]/table/tbody/tr[1]/td/div[#class='wstitle']/a/text()").extract()
self.logger.info(u'---------------success----------------')
When I try my script with driver = webdriver.Chrome(), sel.xpath("//div[#class='dataItem'] gives the desired content and everything works fine. But when I instead use driver = webdriver.PhantomJS(), sel.xpath("//div[#class='dataItem'] is empty. I have try to use WebDriverWait after driver.get() to make the page fully loaded, but it does not work.
You might try this:
driver = webdriver.PhantomJS('add your directory of phantomjs here')
I run a query in one web page, then I get result url. If I right click see html source, I can see the html code generated by JS. If I simply use urllib, python cannot get the JS code. So I see some solution using selenium. Here's my code:
from selenium import webdriver
url = 'http://www.archives.com/member/Default.aspx?_act=VitalSearchResult&lastName=Smith&state=UT&country=US&deathYear=2004&deathYearSpan=10&location=UT&activityID=9b79d578-b2a7-4665-9021-b104999cf031&RecordType=2'
driver = webdriver.PhantomJS(executable_path='C:\python27\scripts\phantomjs.exe')
driver.get(url)
print driver.page_source
>>> <html><head></head><body></body></html> Obviously It's not right!!
Here's the source code I need in right click windows, (I want the INFORMATION part)
</script></div><div class="searchColRight"><div id="topActions" class="clearfix
noPrint"><div id="breadcrumbs" class="left"><a title="Results Summary"
href="Default.aspx? _act=VitalSearchR ...... <<INFORMATION I NEED>> ...
to view the entire record.</p></div><script xmlns:msxsl="urn:schemas-microsoft-com:xslt">
jQuery(document).ready(function() {
jQuery(".ancestry-information-tooltip").actooltip({
href: "#AncestryInformationTooltip", orientation: "bottomleft"});
});
So my question is: How to get the information generated by JS?
You will need to get get the document via javascript you can use seleniums execute_script function
from time import sleep # this should go at the top of the file
sleep(5)
html = driver.execute_script("return document.getElementsByTagName('html')[0].innerHTML")
print html
That will get everything inside of the <html> tag
It's not necessary to use that workaround, you can use instead:
driver = webdriver.PhantomJS()
driver.get('http://www.google.com/')
html = driver.find_element_by_tag_name('html').get_attribute('innerHTML')
I have same problem about getting Javascript sourcecode from Internet, and I solved it using above Victory's suggestion.
*First: execute_script
driver=webdriver.Chrome()
driver.get(urls)
innerHTML = driver.execute_script("return document.body.innerHTML")
#print(driver.page_source)
*Second: parse html using beautifulsoup (You can Downloaded beautifulsoup by pip command)
import bs4 #import beautifulsoup
import re
from time import sleep
sleep(1) #wait one second
root=bs4.BeautifulSoup(innerHTML,"lxml") #parse HTML using beautifulsoup
viewcount=root.find_all("span",attrs={'class':'short-view-count style-scope yt-view-count-renderer'}) #find the value which you need.
*Third: print out the value you need
for span in viewcount:
print(span.string)
*Full code
from selenium import webdriver
import lxml
urls="http://www.archives.com/member/Default.aspx?_act=VitalSearchResult&lastName=Smith&state=UT&country=US&deathYear=2004&deathYearSpan=10&location=UT&activityID=9b79d578-b2a7-4665-9021-b104999cf031&RecordType=2"
driver = webdriver.PhantomJS()
##driver=webdriver.Chrome()
driver.get(urls)
innerHTML = driver.execute_script("return document.body.innerHTML")
##print(driver.page_source)
import bs4
import re
from time import sleep
sleep(1)
root=bs4.BeautifulSoup(innerHTML,"lxml")
viewcount=root.find_all("span",attrs={'class':'short-view-count style-scope yt-view-count-renderer'})
for span in viewcount:
print(span.string)
driver.quit()
I am thinking that you are getting the source code before the JavaScript has rendered the dynamic HTML.
Initially try putting a few seconds sleep between the navigate and get page source.
If this works, then you can change to a different wait strategy.
You try Dryscrape this browser is fully supported heavy js codes try it i hope it work for you
I met the same problem and finally solved by desired_capabilities.
from selenium import webdriver
from selenium.webdriver.common.proxy import Proxy
from selenium.webdriver.common.proxy import ProxyType
proxy = Proxy(
{
'proxyType': ProxyType.MANUAL,
'httpProxy': 'ip_or_host:port'
}
)
desired_capabilities = webdriver.DesiredCapabilities.PHANTOMJS.copy()
proxy.add_to_capabilities(desired_capabilities)
driver = webdriver.PhantomJS(desired_capabilities=desired_capabilities)
driver.get('test_url')
print driver.page_source
I need to extract all calendar data from page like
"http://www.dukascopy.com/swiss/english/marketwatch/calendars/eccalendar/". Firstly - to extract all html with inner dom.
Using eclipse and Python 3.3, win7. Searched here answers, and coded smth based on them.
Looks like:
from PySide import QtGui, QtDeclarative
from PySide.QtGui import QApplication, QDesktopServices, QImage, QPainter
from PySide.QtCore import QByteArray, QUrl, QTimer, QEventLoop, QIODevice, QObject
from PySide.QtWebKit import QWebFrame, QWebView, QWebPage, QWebSettings
from PySide.QtNetwork import QNetworkAccessManager, QNetworkProxy, QNetworkRequest, QNetworkReply, QNetworkDiskCache
#!/usr/bin/env python
"""
app = QApplication(sys.argv)
web = QWebView()
web.load(QUrl("http://www.dukascopy.com/swiss/english/marketwatch/calendars/eccalendar/"))
web.show()
sys.exit(app.exec_())
"""
app = QApplication(sys.argv)
w = QWebView()
request = QNetworkRequest(QUrl("http://www.dukascopy.com/swiss/english/marketwatch/calendars/eccalendar/"))
reply = w.page().networkAccessManager().get(request)
print(reply)
byte_array = reply.readAll()
plist = reply.rawHeaderList()
print(plist)
print(byte_array)
When loading page to QWebView() it works fine (commented code), but I couldn't find how to extract all html from QWebView(). So i tried via "request" - decommented code. And nothing prints.
Try with signals:
def print_content():
print web.page().mainFrame().toHtml() # or toPlainText()
# or
# print web.page().currentFrame().toHtml() # or toPlainText()
and
web.page().mainFrame().loadFinished.connect(print_content)
# or web.loadFinished.connect(print_content)
web.load(QUrl("http://www.dukascopy.com/swiss/english/marketwatch/calendars/eccalendar/"))
web.show()
print_content should be called then loadFinished signal arrives